© 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. 12223
    Prev
    Next
    INDEX
    Explanations

    sums and totals

    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
     sozialen
    -0.96
     Notwendigkeit
    -0.94
     examples
    -0.94
     discover
    -0.93
     what
    -0.93
     Mehrheit
    -0.93
     or
    -0.91
     comprender
    -0.91
     Persönlichkeit
    -0.90
     Glaubens
    -0.90
    POSITIVE LOGITS
    antMatchers
    1.03
     Fazit
    1.03
     Geben
    0.98
     Totals
    0.97
     fous
    0.96
     پایان
    0.94
     pistes
    0.94
     traitements
    0.94
     Infir
    0.94
     Conclusions
    0.93
    Activations Density 0.008%

    No Known Activations