© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58482
    Prev
    Next
    INDEX
    Explanations

    Greenwich Village, gymnasium, duodenal, viaduct

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

    names of educational or institutional buildings like "Greenwich Village," "Lyceum," "Gymnasium," and similar locations.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    慊
    -3.34
    栳
    -3.27
    鰾
    -3.03
     Família
    -2.63
     However
    -2.45
     Roughly
    -2.44
    咤
    -2.38
     Indeed
    -2.38
    𖤣
    -2.38
     Geografia
    -2.36
    POSITIVE LOGITS
    '
    3.95
    "
    3.16
    }
    3.06
    A
    3.05
    ↵↵
    2.97
    8
    2.97
    4
    2.94
    in
    2.83
    3
    2.83
    2
    2.81
    Activations Density 0.008%

    No Known Activations