© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129938
    Prev
    Next
    INDEX
    Explanations

    code constructs

    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
     Kategorie
    -1.16
    
    -1.13
     œufs
    -1.08
     fizeram
    -1.03
     nochmals
    -1.03
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -1.03
     kialak
    -1.02
    
    -1.02
     centaines
    -1.02
     своем
    -1.00
    POSITIVE LOGITS
     from
    1.63
     before
    1.61
     one
    1.28
     and
    1.27
     when
    1.26
     to
    1.08
     When
    1.05
     so
    1.00
     or
    1.00
     if
    0.99
    Activations Density 0.004%

    No Known Activations