© 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. 12233
    Prev
    Next
    INDEX
    Explanations

    names and suffixes

    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
    messung
    -1.39
    電影
    -1.39
     Erhöhung
    -1.33
    urlaub
    -1.31
    tasche
    -1.31
    曾經
    -1.31
     nœ
    -1.26
    來自
    -1.26
    我們
    -1.25
     cuisson
    -1.24
    POSITIVE LOGITS
     now
    1.35
     so
    1.35
     to
    1.34
     due
    1.28
     US
    1.22
     was
    1.20
     not
    1.19
     rootReducer
    1.16
     $
    1.16
     AA
    1.13
    Activations Density 0.020%

    No Known Activations