© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 1133
    Prev
    Next
    INDEX
    Explanations

    xml declaration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     monoton
    0.51
     amputation
    0.47
     суть
    0.46
    ColorBit
    0.46
     ампли
    0.45
    皁
    0.44
    㐹
    0.44
    OutgoingRiver
    0.44
    تحان
    0.44
     rück
    0.43
    POSITIVE LOGITS
    x
    0.55
    xml
    0.50
     J
    0.48
    DOCTYPE
    0.47
    XML
    0.47
    ID
    0.46
    io
    0.46
     XML
    0.46
    company
    0.46
    icon
    0.46
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.