© 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. 34-GEMMASCOPE-RES-131K
    7. 63455
    Prev
    Next
    INDEX
    Explanations

    Follow Us

    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_34/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
    AAF
    -0.77
     Map
    -0.72
    واء
    -0.71
    崩
    -0.70
    もある
    -0.69
    航
    -0.69
     दूर
    -0.67
    -)
    -0.67
    回归
    -0.66
    ем
    -0.65
    POSITIVE LOGITS
    EPS
    0.95
     EPS
    0.95
     CRS
    0.93
    CRS
    0.88
    Père
    0.85
     Napoléon
    0.82
    脸上的
    0.81
    ROG
    0.79
    Piazza
    0.79
    deleteById
    0.77
    Activations Density 0.012%

    No Known Activations