© 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. 36355
    Prev
    Next
    INDEX
    Explanations

    technical concepts and materials

    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
    “
    -1.07
    >
    -0.90
    return
    -0.88
    i
    -0.86
    开心
    -0.85
    valla
    -0.85
    ，
    -0.85
    ductors
    -0.85
    "
    -0.84
     “
    -0.82
    POSITIVE LOGITS
     prazer
    1.00
    berikut
    0.98
    decoración
    0.98
    uszcz
    0.97
    卽
    0.96
    怎么回事
    0.95
    させて頂きます
    0.95
     kabát
    0.93
    徬
    0.92
     oeil
    0.91
    Activations Density 0.415%

    No Known Activations