Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12110
    Prev
    Next
    INDEX
    Explanations

    dates and approvals

    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
     recently
    -1.77
     Recently
    -1.48
     recent
    -1.31
     can
    -1.24
     these
    -1.23
    Recently
    -1.20
    每次
    -1.19
     currently
    -1.18
     lately
    -1.16
     regularly
    -1.15
    POSITIVE LOGITS
     yesterday
    1.59
     tonight
    1.37
     Wednesday
    1.37
     Thursday
    1.34
     diriger
    1.32
     today
    1.30
     finalement
    1.28
     schuldig
    1.28
    etna
    1.24
     hôm
    1.23
    Activations Density 0.204%

    No Known Activations