© 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. 34-GEMMASCOPE-RES-131K
    7. 59431
    Prev
    Next
    INDEX
    Explanations

    feature requests and suggestions

    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
     ند
    -0.80
    Choosing
    -0.79
     твое
    -0.75
    licula
    -0.74
     maging
    -0.74
     questioning
    -0.73
    calling
    -0.73
    谙
    -0.73
    UpdatedAt
    -0.73
     colch
    -0.73
    POSITIVE LOGITS
     feature
    2.31
    Feature
    2.22
     Feature
    2.13
    feature
    1.98
     features
    1.81
    要望
    1.77
     enhancement
    1.74
     votes
    1.70
    FEATURE
    1.67
     suggestion
    1.61
    Activations Density 0.073%

    No Known Activations