© 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. 11315
    Prev
    Next
    INDEX
    Explanations

    unexpected but

    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
     nuoc
    -0.88
    jshint
    -0.82
    ﹕
    -0.81
     vorige
    -0.80
     descomp
    -0.79
    тябрь
    -0.79
    cesso
    -0.79
     trennen
    -0.79
    ◪
    -0.79
     kana
    -0.78
    POSITIVE LOGITS
     occasionally
    1.36
     still
    1.24
     exceptions
    1.20
     sometimes
    1.09
     trotzdem
    0.97
     dennoch
    0.95
     permitted
    0.91
     nevertheless
    0.90
     allow
    0.90
     occasional
    0.89
    Activations Density 0.068%

    No Known Activations