© 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. 12187
    Prev
    Next
    INDEX
    Explanations

    mathematical or factual questions

    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
     usati
    -1.17
    Ecotoxicity
    -1.16
    امن
    -1.10
     utilizzati
    -1.05
    immen
    -1.05
    WithFormat
    -1.04
     giudice
    -1.04
    /",
    -1.00
    kish
    -1.00
    Both
    -1.00
    POSITIVE LOGITS
     ensuing
    1.18
     astute
    1.02
    WRONG
    1.00
     also
    0.98
    结束了
    0.96
     notifying
    0.96
    tr
    0.95
    没能
    0.94
     nécessaires
    0.94
     rasgos
    0.94
    Activations Density 0.055%

    No Known Activations