© 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. 1414
    Prev
    Next
    INDEX
    Explanations

    -sized

    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
     capítulo
    -0.97
    ünde
    -0.83
    пят
    -0.82
    ţii
    -0.79
     aina
    -0.77
    mış
    -0.77
    bieten
    -0.77
     loopt
    -0.76
    èse
    -0.75
    亹
    -0.75
    POSITIVE LOGITS
    AndPassword
    0.77
     někter
    0.75
     fantastic
    0.74
    δά
    0.74
    <h3>
    0.74
    ៹
    0.73
    ujące
    0.72
    AYLOR
    0.72
    とい
    0.71
     projected
    0.71
    Activations Density 0.004%

    No Known Activations