© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74106
    Prev
    Next
    INDEX
    Explanations

    hexadecimal identifiers and addresses

    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
    vantaged
    -2.63
    癀
    -2.36
    </h3>
    -2.36
    ⎆
    -2.13
    嵛
    -2.11
    that
    -1.98
    鹚
    -1.95
    ᐕ
    -1.91
     identifiés
    -1.90
     tattered
    -1.85
    POSITIVE LOGITS
    \
    2.67
     you
    2.09
     continuamente
    1.67
    芎
    1.62
    を行
    1.62
     Offizielle
    1.55
    },
    1.52
    夤
    1.51
     elog
    1.51
    りに
    1.49
    Activations Density 0.010%

    No Known Activations