© 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. 129468
    Prev
    Next
    INDEX
    Explanations

    sludge thickening, oil, school courses

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

    valued, able, school, billing, low

    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
    сить
    0.57
    Incrementor
    0.53
    瑗
    0.52
    мс
    0.51
    ні
    0.51
    赢得
    0.50
    嚜
    0.50
     колле
    0.49
    ண்க
    0.49
    сія
    0.48
    POSITIVE LOGITS
     is
    0.64
     =
    0.63
     to
    0.61
     trauma
    0.58
     initialization
    0.54
    j
    0.54
     traw
    0.53
     literature
    0.53
     loads
    0.53
    I
    0.52
    Activations Density 0.000%

    No Known Activations