© 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. 47481
    Prev
    Next
    INDEX
    Explanations

    related literature or code examples

    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
    轰隆
    -1.86
     ў
    -1.63
    轰隆隆
    -1.63
    zembro
    -1.57
    咔嚓
    -1.56
     новогод
    -1.49
    戦う
    -1.49
     ANGELES
    -1.48
    😹
    -1.46
    崂
    -1.42
    POSITIVE LOGITS
     there
    2.03
     like
    1.98
     are
    1.95
     such
    1.79
     albeit
    1.72
     relevant
    1.70
     here
    1.52
    と思ったら
    1.52
    There
    1.52
     similar
    1.51
    Activations Density 0.014%

    No Known Activations