© 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. 225657
    Prev
    Next
    INDEX
    Explanations

    object descriptions

    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
    j
    0.54
    បង្កើត
    0.52
    ->
    0.50
     ニュー
    0.47
     ସ
    0.47
     સુર
    0.46
     ->
    0.46
     無
    0.46
     言
    0.46
     impress
    0.45
    POSITIVE LOGITS
     conocida
    0.54
    빗
    0.49
    äksi
    0.48
     sólida
    0.48
    тана
    0.45
    닥
    0.45
     Kategorie
    0.44
     Scandinavia
    0.44
     ornamentation
    0.43
    PrototypeOf
    0.42
    Activations Density 0.000%

    No Known Activations