© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 110654
    Prev
    Next
    INDEX
    Explanations

    outer limits

    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_34/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
    ICTO
    -0.82
     価格
    -0.76
    nition
    -0.75
    Дина
    -0.73
    テキ
    -0.73
     inside
    -0.73
     Axes
    -0.70
    uteness
    -0.70
     الداخلية
    -0.70
    lanation
    -0.69
    POSITIVE LOGITS
    limits
    1.21
     shell
    1.18
     limits
    1.15
     Outer
    1.14
     Limits
    1.14
    Outer
    1.09
    outer
    1.05
     layer
    1.02
     outer
    1.02
     periphery
    1.00
    Activations Density 0.017%

    No Known Activations