© 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. 44302
    Prev
    Next
    INDEX
    Explanations

    journal citations with numbers

    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
    ↵↵
    -1.89
    J
    -1.75
    <tr>
    -1.75
    D
    -1.59
     also
    -1.57
    。（
    -1.56
    ">
    -1.55
    -1.49
    )
    -1.48
     大
    -1.47
    POSITIVE LOGITS
     柄
    1.60
    those
    1.60
     différences
    1.59
    𖣔
    1.58
     célèbres
    1.53
     női
    1.51
    𐄁
    1.46
    -
    1.45
     hakkında
    1.43
     Ně
    1.43
    Activations Density 0.121%

    No Known Activations