© 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. 10-GEMMASCOPE-RES-131K
    7. 119000
    Prev
    Next
    INDEX
    Explanations

    heterogeneous group

    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
    鮓
    -2.69
    🦣
    -2.56
    琹
    -2.52
    ⑉
    -2.50
     When
    -2.48
    %),
    -2.45
    逦
    -2.45
    when
    -2.45
    维修
    -2.44
     cihaz
    -2.38
    POSITIVE LOGITS
     of
    3.44
    0
    3.19
    感じで
    3.08
     như
    2.39
    >
    2.38
     delightful
    2.36
    感じです
    2.31
     związane
    2.31
    なんだか
    2.28
     spearheaded
    2.28
    Activations Density 0.006%

    No Known Activations