© 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. 77186
    Prev
    Next
    INDEX
    Explanations

    Dispose (

    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
    бие
    -0.74
    нитар
    -0.70
     abide
    -0.68
    eventType
    -0.68
     nội
    -0.67
     geometr
    -0.65
     geometric
    -0.65
    натор
    -0.64
     out
    -0.63
    pezi
    -0.63
    POSITIVE LOGITS
    iteration
    0.78
    Công
    0.73
    禎
    0.73
    corner
    0.72
    specialchars
    0.72
    钳
    0.72
    💦
    0.71
     comb
    0.71
     COMMENTS
    0.70
    Iteration
    0.69
    Activations Density 0.073%

    No Known Activations