© 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. 74905
    Prev
    Next
    INDEX
    Explanations

    academic citations

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

    never reaches

    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
    ном
    0.52
    탈
    0.51
     进行
    0.50
    യിലൂടെ
    0.49
    ین
    0.48
    สาน
    0.48
    ンの
    0.48
     コンパクト
    0.47
    気に
    0.46
    ഭ
    0.46
    POSITIVE LOGITS
     empirically
    0.50
    '
    0.46
     duvet
    0.46
     beginners
    0.45
     stimulant
    0.44
     particolarmente
    0.43
     physi
    0.42
     genuinely
    0.42
     brighter
    0.42
     enzymatic
    0.42
    Activations Density 0.000%

    No Known Activations