© 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. 13303
    Prev
    Next
    INDEX
    Explanations

    dates and years

    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
     Its
    -2.20
    ᯾
    -2.20
    艽
    -2.11
    ﾔ
    -2.06
     žen
    -2.05
    ارتمان
    -2.05
    çek
    -2.03
    哙
    -2.00
    
    -1.98
    的心情
    -1.98
    POSITIVE LOGITS
     —
    2.73
    or
    2.42
    on
    2.19
     erstes
    2.11
    ‘
    2.06
    ↵↵
    2.05
     großes
    1.95
     нескольких
    1.90
     eigenes
    1.84
     neues
    1.84
    Activations Density 0.087%

    No Known Activations