© 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. 34-GEMMASCOPE-RES-131K
    7. 78935
    Prev
    Next
    INDEX
    Explanations

    web dialog helper registry transparency notification wrapper

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

    The neuron specializes in spotting file‐path strings (particularly those appearing in #include directives).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    qli
    -0.77
     SMITH
    -0.75
     doubt
    -0.75
     podremos
    -0.74
    ってください
    -0.73
    ouching
    -0.73
    SIGNATURE
    -0.69
     democrats
    -0.69
    かって
    -0.69
     diámetro
    -0.69
    POSITIVE LOGITS
    "));
    0.76
     pilote
    0.75
    ILA
    0.72
    bria
    0.71
     interfaz
    0.70
    ứ
    0.70
    Decided
    0.70
    Ơ
    0.69
    ullah
    0.69
    ViewInit
    0.69
    Activations Density 0.052%

    No Known Activations