© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116542
    Prev
    Next
    INDEX
    Explanations

    and/or other

    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
    붕
    -0.76
    inii
    -0.72
     Perio
    -0.70
    alit
    -0.70
    enstein
    -0.69
    arion
    -0.66
    招待
    -0.66
    Created
    -0.65
    haraan
    -0.65
    oners
    -0.65
    POSITIVE LOGITS
    bati
    0.75
     cuarentena
    0.69
     попу
    0.69
     buffering
    0.67
    getInput
    0.66
    pova
    0.65
    Downloads
    0.65
     निर्देश
    0.64
     adulto
    0.63
    paz
    0.63
    Activations Density 0.084%

    No Known Activations