© 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. 12325
    Prev
    Next
    INDEX
    Explanations

    coding:

    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
     différents
    -1.56
    踯
    -1.52
     différentes
    -1.52
    
    -1.52
    驺
    -1.51
    
    -1.50
     DIFFERENT
    -1.48
    
    -1.45
     wiele
    -1.45
    
    -1.43
    POSITIVE LOGITS
     for
    1.71
     in
    1.70
     at
    1.59
     or
    1.55
    Although
    1.47
     on
    1.38
    </em>
    1.37
    Some
    1.36
     under
    1.34
     took
    1.34
    Activations Density 0.027%

    No Known Activations