© 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. 44349
    Prev
    Next
    INDEX
    Explanations

    seafood

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

    words or phrases related to seafood and marine contexts.

    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
    geſ
    -2.72
    <td>
    -2.48
    \
    -2.33
    bumptech
    -2.31
     However
    -2.17
    1
    -2.17
     большим
    -2.05
    انی
    -1.99
    ......
    -1.97
     Для
    -1.96
    POSITIVE LOGITS
     deliciosos
    2.66
    𖧵
    2.48
    糗
    2.47
    ⑊
    2.38
    篭
    2.31
     conç
    2.30
    沵
    2.30
    物が
    2.25
    いろんな
    2.20
    s
    2.19
    Activations Density 0.001%

    No Known Activations