© 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. 22-GEMMASCOPE-RES-131K
    7. 36266
    Prev
    Next
    INDEX
    Explanations

    typing or typed text

    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_22/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
     —
    -2.53
    ↵
    -2.48
     –
    -2.34
    "
    -2.17
    '
    -2.13
    v
    -2.06
    T
    -2.06
    IN
    -1.97
     is
    -1.97
    ….
    -1.93
    POSITIVE LOGITS
    geſ
    2.73
    샅
    2.14
    夢見
    1.89
    
    1.85
    旆
    1.84
    釭
    1.84
     arranque
    1.81
    gebnisse
    1.80
    Ᏹ
    1.80
     ofreci
    1.79
    Activations Density 0.012%

    No Known Activations