© 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. 10-GEMMASCOPE-RES-131K
    7. 28985
    Prev
    Next
    INDEX
    Explanations

    styled shoots

    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_10/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
     not
    -1.76
     newfound
    -1.56
    了不少
    -1.56
    tanleria
    -1.49
     naciones
    -1.48
     unforgettable
    -1.46
     pirm
    -1.44
    碉
    -1.43
     importantes
    -1.41
     iglesias
    -1.41
    POSITIVE LOGITS
    骓
    1.70
    肏
    1.65
     perles
    1.55
    骉
    1.50
     woorden
    1.49
    它
    1.46
    ooh
    1.45
     ∼
    1.45
    記得
    1.45
    ”，
    1.45
    Activations Density 0.000%

    No Known Activations