© 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. 44019
    Prev
    Next
    INDEX
    Explanations

    enough to take action

    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
    </i>
    -2.02
     \%$
    -1.52
    """
    -1.52
    o
    -1.41
    螈
    -1.38
     Hæ
    -1.34
    ;
    -1.32
    ные
    -1.31
     as
    -1.27
     Then
    -1.26
    POSITIVE LOGITS
    怍
    1.86
    橚
    1.83
     mété
    1.78
    咴
    1.78
     огром
    1.77
    atguigu
    1.76
    鍇
    1.75
     lança
    1.73
    嫫
    1.73
    breviations
    1.71
    Activations Density 0.015%

    No Known Activations