© 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. 21548
    Prev
    Next
    INDEX
    Explanations

    transco maintenance

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

    avoiding premature judgment or limitations

    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
    ar
    0.60
    ;
    0.59
    ac
    0.57
    hak
    0.57
    ul
    0.56
    ad
    0.55
    ate
    0.53
    ↵
    0.52
    an
    0.52
    ir
    0.52
    POSITIVE LOGITS
     observación
    0.63
     mantenimiento
    0.58
     mantener
    0.57
     mantenere
    0.56
     minimizar
    0.56
     imprescind
    0.55
     inclusión
    0.55
     detener
    0.54
     manutenção
    0.54
     elimina
    0.54
    Activations Density 0.000%

    No Known Activations