© 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. 111174
    Prev
    Next
    INDEX
    Explanations

    exciting changes or science pathway

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

    standard development

    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
     {
    0.51
     VARI
    0.49
     DAILY
    0.47
     VISIT
    0.46
     [
    0.46
     ),
    0.44
     endeavors
    0.43
    ตู
    0.43
     borders
    0.43
     TypeError
    0.42
    POSITIVE LOGITS
    equipped
    0.49
    actually
    0.48
     பக்க
    0.48
    ^{*}
    0.46
    க்கப்படுகிறது
    0.46
     perempt
    0.46
    erweise
    0.46
     majest
    0.46
     इच्छुक
    0.45
    graphHead
    0.45
    Activations Density 0.000%

    No Known Activations