© 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. 109435
    Prev
    Next
    INDEX
    Explanations

    JSON or array structures

    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
     Lo
    -0.76
     αντι
    -0.73
     açık
    -0.73
     bullet
    -0.72
     recre
    -0.71
     Bert
    -0.71
     Harry
    -0.69
    ButtonItem
    -0.67
     sk
    -0.66
    tifier
    -0.66
    POSITIVE LOGITS
     Cerr
    0.70
    áno
    0.64
     Countess
    0.63
     Zeke
    0.63
    vosť
    0.63
    HART
    0.62
    精选
    0.62
     upwards
    0.61
     puzzled
    0.61
    Gemeinde
    0.61
    Activations Density 0.042%

    No Known Activations