© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 678
    Prev
    Next
    INDEX
    Explanations

    UserId and require paths

    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
    毉
    -2.92
     have
    -2.92
    疴
    -2.81
     เรา
    -2.70
    瑗
    -2.64
    䊐
    -2.63
    鼍
    -2.53
     of
    -2.53
    幇
    -2.45
    潆
    -2.41
    POSITIVE LOGITS
    i
    3.64
    This
    3.63
    With
    3.42
    Having
    3.42
    \
    3.34
    on
    3.25
    From
    3.14
    Since
    3.00
    Just
    3.00
    Like
    3.00
    Activations Density 0.005%

    No Known Activations