© 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. 62914
    Prev
    Next
    INDEX
    Explanations

    nested list to flat list

    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
     soreness
    -0.80
    chaic
    -0.77
     intención
    -0.76
     ждать
    -0.76
     menambah
    -0.75
     espont
    -0.75
     ["",
    -0.74
    komfort
    -0.73
    onBlur
    -0.73
    semver
    -0.72
    POSITIVE LOGITS
     flatten
    1.55
    flatten
    1.43
    flat
    1.38
     flattened
    1.38
     flat
    1.35
    Flatten
    1.34
     Flatten
    1.31
     flattening
    1.16
     total
    1.13
    numel
    1.09
    Activations Density 0.014%

    No Known Activations