© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103788
    Prev
    Next
    INDEX
    Explanations

    Frameworks and http strings

    np_acts-logits-general · gemini-2.5-flash-lite

    programming language comments or declarations that specify encoding, file format, or framework metadata (particularly "frozen_string_literal", "Framework", "DTD", and HTTP headers).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on code‐oriented boilerplate keywords (like framework/class names, language pragmas, and metadata attributes).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     muitos
    -1.85
    y
    -1.73
     alguns
    -1.66
     have
    -1.58
     muitas
    -1.57
     einigen
    -1.55
     are
    -1.55
    r
    -1.52
     in
    -1.45
     bazı
    -1.41
    POSITIVE LOGITS
     "}";
    1.88
     bluza
    1.84
     "]";
    1.74
     ſame
    1.57
     porcelaine
    1.51
    pantalones
    1.48
    豳
    1.45
    čet
    1.44
     Dernière
    1.44
    ところです
    1.42
    Activations Density 0.033%

    No Known Activations