© 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. 125754
    Prev
    Next
    INDEX
    Explanations

    immediately after, delete the, realize what

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

    Detective/legal cases

    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
     Polaribacter
    0.47
    guien
    0.45
    有一个
    0.41
    (',',
    0.41
    sadpoetry
    0.40
    shapeColor
    0.40
    끗
    0.40
     striped
    0.40
    出去
    0.40
     deduced
    0.40
    POSITIVE LOGITS
    ia
    0.48
    H
    0.48
     ern
    0.47
     Thornton
    0.46
    J
    0.46
    Brien
    0.45
    ss
    0.44
     учеб
    0.44
    lland
    0.44
     он
    0.43
    Activations Density 0.000%

    No Known Activations