© 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. 38772
    Prev
    Next
    INDEX
    Explanations

    nominee, goalie, opponent

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    A
    -3.97
    on
    -3.58
    K
    -3.30
    」
    -3.17
     '
    -3.08
    c
    -3.08
    )$
    -3.03
    en
    -3.03
    。
    -3.00
    le
    -2.98
    POSITIVE LOGITS
    尨
    3.41
    蚡
    3.36
    泚
    2.97
    蟜
    2.97
    狴
    2.91
     ་
    2.88
    Ꮚ
    2.84
    岽
    2.77
    缯
    2.77
     parachoque
    2.69
    Activations Density 0.003%

    No Known Activations