© 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. 128042
    Prev
    Next
    INDEX
    Explanations

    instance for

    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
    }$
    -2.69
    甞
    -2.67
     unſ
    -2.55
    廕
    -2.53
     ワイド
    -2.38
    孩子
    -2.36
    翫
    -2.33
     réfugi
    -2.31
     Fläche
    -2.28
    嫑
    -2.28
    POSITIVE LOGITS
    <bos>
    3.16
     для
    3.00
     For
    2.92
     για
    2.58
     Then
    2.56
     Interestingly
    2.56
    ).
    2.52
    providedIn
    2.52
    al
    2.48
    ஂ
    2.48
    Activations Density 0.017%

    No Known Activations