© 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. 10-GEMMASCOPE-RES-131K
    4. 739
    Prev
    Next
    INDEX
    Explanations

    proper nouns and abbreviations

    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
    and
    -3.20
    >
    -3.09
    曾在
    -2.86
    u
    -2.63
     Pourquoi
    -2.47
    .
    -2.39
     駅前
    -2.36
    0
    -2.33
    ing
    -2.30
    3
    -2.30
    POSITIVE LOGITS
    ↵↵
    3.38
    ?"
    2.70
    jface
    2.45
    StoryboardSegue
    2.45
    в
    2.44
     This
    2.39
    瑧
    2.34
     experimenting
    2.33
    
    2.33
    besondere
    2.31
    Activations Density 0.024%

    No Known Activations