© 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. 10711
    Prev
    Next
    INDEX
    Explanations

    organizations, names, and foreign words

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

    Gödel, Escher, Bach

    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
     daz
    0.39
    }$.
    0.37
     ফ
    0.35
     +
    0.35
     wobei
    0.35
     combinatorial
    0.34
     Einstellungen
    0.34
     kaks
    0.34
    ≙
    0.34
    durch
    0.33
    POSITIVE LOGITS
     முய
    0.32
    よかった
    0.31
     Fellow
    0.30
    做好
    0.30
     Veterans
    0.30
     लोकतांत्रिक
    0.30
     अवज्ञा
    0.30
     democracia
    0.29
     অভিযান
    0.29
     urges
    0.29
    Activations Density 0.040%

    No Known Activations