© 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. 115136
    Prev
    Next
    INDEX
    Explanations

    foreign nouns and adjectives

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

    travel directions

    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
     सत्तार
    0.52
    Ruling
    0.49
    Cultural
    0.48
    Construction
    0.47
    ഗീയ
    0.47
    }}\
    0.45
    Justice
    0.45
    अप
    0.44
    Civil
    0.44
    వారి
    0.44
    POSITIVE LOGITS
     座
    0.48
     peint
    0.46
     購入
    0.45
     interess
    0.45
     Cous
    0.45
     reales
    0.45
     visites
    0.45
     Hôtel
    0.44
     mence
    0.44
     beneficia
    0.44
    Activations Density 0.001%

    No Known Activations