© 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. 80285
    Prev
    Next
    INDEX
    Explanations

    definition at line

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

    code snippets and keywords

    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
    STOP
    0.45
    TON
    0.43
    BURN
    0.42
    学者
    0.40
     американ
    0.39
     GOLD
    0.39
    깁
    0.39
    ूत
    0.39
    styr
    0.39
    テント
    0.38
    POSITIVE LOGITS
     heartily
    0.42
     endif
    0.41
     ascribe
    0.41
     ഭൂ
    0.40
     použív
    0.40
     operativos
    0.40
     Vamos
    0.39
     použí
    0.39
     vamos
    0.38
     #-}
    0.38
    Activations Density 0.001%

    No Known Activations