© 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. 10-GEMMASCOPE-RES-131K
    7. 43878
    Prev
    Next
    INDEX
    Explanations

    Mok | IBS | SPECT | addNew

    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
     ujedno
    -2.67
     火锅
    -2.58
    除此之外
    -2.58
     niedersachsen
    -2.56
    acterísticas
    -2.56
    毟
    -2.53
     ブログ
    -2.53
    酹
    -2.52
    
    -2.47
    ﹊
    -2.45
    POSITIVE LOGITS
    -
    4.16
    d
    4.03
    ↵↵
    3.83
    3
    3.53
    2
    3.44
    ",
    3.41
    1
    3.34
    –
    3.19
    (
    3.11
     -
    3.06
    Activations Density 0.017%

    No Known Activations