© 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. 161706
    Prev
    Next
    INDEX
    Explanations

    decade of research

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

    your followed by day or very

    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
    b
    0.46
    ba
    0.44
    epsilon
    0.44
    ang
    0.43
    var
    0.42
    bär
    0.42
    ும்ப
    0.41
    bu
    0.41
    caret
    0.40
    toLocale
    0.40
    POSITIVE LOGITS
     blower
    0.45
    䟧
    0.45
     హిట్
    0.44
     剤
    0.44
     ionization
    0.42
     তরঙ্গ
    0.42
     熱
    0.42
     meestal
    0.42
     cytokine
    0.41
     Convolution
    0.41
    Activations Density 0.000%

    No Known Activations