© 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. 99398
    Prev
    Next
    INDEX
    Explanations

    what you

    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
     will
    -1.58
    ”,
    -1.38
    ↵↵
    -1.34
    R
    -1.31
     of
    -1.30
     abbraccio
    -1.30
    ”
    -1.28
    」,
    -1.27
    の場合
    -1.24
    =“
    -1.23
    POSITIVE LOGITS
    <mask>
    1.37
     Drž
    1.36
    </b>
    1.33
     theyre
    1.25
    加減
    1.24
     μόνο
    1.23
    描き
    1.20
     They
    1.18
    してました
    1.17
    Kreuz
    1.16
    Activations Density 0.014%

    No Known Activations