© 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. 32323
    Prev
    Next
    INDEX
    Explanations

    categories and titles

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

    urls ending with/pages or /articles

    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
     was
    0.47
    般的
    0.42
    keepers
    0.41
     briefs
    0.41
     Eats
    0.41
    UEN
    0.41
    的
    0.41
    लों
    0.40
    LAN
    0.40
     Після
    0.39
    POSITIVE LOGITS
     couleur
    0.49
    nv
    0.46
     ફરિયાદ
    0.46
    lhe
    0.45
    %。
    0.44
     culoare
    0.43
    itet
    0.42
    harma
    0.42
     sentimiento
    0.42
     jugu
    0.42
    Activations Density 0.003%

    No Known Activations