© 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. 22-GEMMASCOPE-RES-131K
    7. 68396
    Prev
    Next
    INDEX
    Explanations

    impossible or otherwise

    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
    ↔
    -0.98
    niest
    -0.98
    ldap
    -0.94
    ˊ
    -0.93
    豋
    -0.92
    麒麟
    -0.91
    leste
    -0.89
    ėj
    -0.88
    eabouts
    -0.88
    yyah
    -0.87
    POSITIVE LOGITS
     otherwise
    1.66
     previously
    1.66
     other
    1.45
     others
    1.45
     not
    1.38
    previously
    1.32
     never
    1.30
     rarely
    1.27
     cannot
    1.25
     heretofore
    1.25
    Activations Density 0.043%

    No Known Activations