© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 166629
    Prev
    Next
    INDEX
    Explanations

    the books of Timothy

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

    harm, require, useful

    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
    Negative Logits
     kucch
    0.51
     darb
    0.50
     mumbai
    0.50
     valueForKey
    0.49
     тура
    0.46
     turntable
    0.45
     maharaja
    0.44
    𝙧
    0.44
     setData
    0.43
     worldRank
    0.43
    POSITIVE LOGITS
    Muchas
    0.43
    Saw
    0.42
    years
    0.42
    중
    0.42
     genus
    0.41
    ヒ
    0.41
    Juven
    0.41
    other
    0.41
    الم
    0.41
    ール
    0.40
    Activations Density 0.001%

    No Known Activations