© 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. 108383
    Prev
    Next
    INDEX
    Explanations

    storageexternal

    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
     side
    -0.74
    라고
    -0.73
     exercices
    -0.70
    ;'>
    -0.69
    gifs
    -0.69
     Durchmesser
    -0.68
    ेड
    -0.66
     baka
    -0.65
    ftar
    -0.65
    folie
    -0.65
    POSITIVE LOGITS
    agg
    0.75
     amistad
    0.71
    aja
    0.70
    accuracy
    0.70
    reverse
    0.69
    ධ
    0.66
    den
    0.65
    ja
    0.64
    credentials
    0.64
    FileStream
    0.63
    Activations Density 0.096%

    No Known Activations