© 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. 91629
    Prev
    Next
    INDEX
    Explanations

    transient stability analysis

    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
     Verne
    -0.77
    melan
    -0.75
    เลข
    -0.68
    伶
    -0.68
    strokeWidth
    -0.68
    のだろうか
    -0.68
    strokeColor
    -0.67
    icare
    -0.67
    するの
    -0.66
    FixedSize
    -0.65
    POSITIVE LOGITS
     Grid
    0.82
    Grid
    0.82
    GRID
    0.79
     Generator
    0.79
    iania
    0.78
    URAS
    0.75
     refunds
    0.75
     Reliability
    0.74
    FER
    0.71
    Generator
    0.71
    Activations Density 0.030%

    No Known Activations