© 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. 22-GEMMASCOPE-RES-131K
    7. 11567
    Prev
    Next
    INDEX
    Explanations

    android and java imports

    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
     add
    -1.38
     makes
    -1.31
     both
    -1.30
     increase
    -1.27
     more
    -1.26
     before
    -1.24
     as
    -1.23
    Both
    -1.22
     seems
    -1.22
    That
    -1.22
    POSITIVE LOGITS
    鲼
    1.53
    weren
    1.37
    ())),
    1.34
    ᯅ
    1.30
    OUGH
    1.30
     ſeveral
    1.29
    
    1.28
    ﹍﹍
    1.28
     rokok
    1.26
    
    1.25
    Activations Density 0.000%

    No Known Activations