© 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. 237940
    Prev
    Next
    INDEX
    Explanations

    Spanish language terms

    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
    list
    0.52
    j
    0.48
     говорю
    0.46
    ref
    0.46
    umber
    0.44
     MANY
    0.44
    l
    0.43
    ieving
    0.43
    g
    0.43
    ll
    0.43
    POSITIVE LOGITS
     jár
    0.52
     cán
    0.51
     División
    0.47
     autón
    0.46
     Fiscalía
    0.45
     geoLocation
    0.44
     deceduto
    0.44
     próxima
    0.42
    园区
    0.42
     orgánica
    0.42
    Activations Density 0.003%

    No Known Activations