© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112413
    Prev
    Next
    INDEX
    Explanations

    configuration files

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

    closing tags or end markers in XML and HTML code.

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

    The neuron flags numeric literal tokens (e.g. integer or decimal values) in structured markup.

    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
     frança
    -2.27
    ☫
    -2.23
    饪
    -2.23
     ilha
    -2.17
    梦见
    -2.16
     elefante
    -2.13
    莚
    -2.09
     ")");
    -2.00
     parede
    -1.99
     recenz
    -1.98
    POSITIVE LOGITS
     
    2.61
    on
    2.11
     to
    1.94
     and
    1.91
    s
    1.88
     is
    1.84
    関する
    1.84
    A
    1.83
     trabajando
    1.80
     or
    1.79
    Activations Density 0.027%

    No Known Activations