© 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. 114740
    Prev
    Next
    INDEX
    Explanations

    concluding words like thus or so

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

    classic, asking, specific, abandon, mission, league, LV

    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
    '
    0.44
    न
    0.43
    <sup>
    0.43
    หวาน
    0.43
    🌡
    0.42
    arial
    0.42
     навча
    0.42
    [
    0.41
    א
    0.41
    ’
    0.41
    POSITIVE LOGITS
    abı
    0.50
    amanya
    0.46
     turnkey
    0.46
     skyrocketed
    0.45
     Теннис
    0.45
    نية
    0.45
     stake
    0.44
     കള
    0.44
     handcuffed
    0.44
     tightened
    0.44
    Activations Density 0.000%

    No Known Activations