© 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. 7531
    Prev
    Next
    INDEX
    Explanations

    code related concepts

    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
     and
    -2.42
    );
    -1.75
    ↵↵↵
    -1.59
     in
    -1.52
    </td>
    -1.48
    ish
    -1.45
    ！　
    -1.42
    -1.41
    ých
    -1.36
     даже
    -1.36
    POSITIVE LOGITS
     Muchos
    1.61
    Vii
    1.52
     boister
    1.50
     Pued
    1.50
    cuz
    1.49
     marito
    1.48
    appeared
    1.47
    ようですが
    1.47
     recente
    1.46
    Cia
    1.46
    Activations Density 0.016%

    No Known Activations