© 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. 22-GEMMASCOPE-RES-131K
    7. 25803
    Prev
    Next
    INDEX
    Explanations

    Miss Fisher's Murder Mysteries

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

    The neuron fires on programming‐language literal values and assignment syntax—e.g. numeric constants, boolean literals, and the “=” operator in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     their
    -1.03
    août
    -0.92
    حيح
    -0.91
     morfo
    -0.90
    các
    -0.90
     Welche
    -0.90
     mitu
    -0.89
    ᄀ
    -0.88
     couper
    -0.88
    ĭ
    -0.87
    POSITIVE LOGITS
     but
    0.95
     групи
    0.92
    柠檬
    0.90
    後は
    0.88
    <0xA3>
    0.85
    默认为
    0.83
     вопросы
    0.82
    介意
    0.82
    来的
    0.82
     strang
    0.80
    Activations Density 0.015%

    No Known Activations