© 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. 110300
    Prev
    Next
    INDEX
    Explanations

    President James Knox Polk

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

    That would be

    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
     회
    0.46
     Pleasure
    0.45
     Alli
    0.44
     此
    0.43
    v
    0.43
     pl
    0.43
     沒有
    0.42
     لم
    0.42
     Wound
    0.42
    हीत
    0.41
    POSITIVE LOGITS
    の人気
    0.45
    ルー
    0.44
    Ferrari
    0.43
    ES
    0.43
    Italian
    0.42
     encarg
    0.42
    }";
    0.42
    Unfortunately
    0.42
    November
    0.42
    Throughout
    0.42
    Activations Density 0.000%

    No Known Activations