© 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. 11462
    Prev
    Next
    INDEX
    Explanations

    important and primary tasks

    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
     to
    -1.10
    ällt
    -0.95
    prechpartner
    -0.93
    ﹝
    -0.88
    embl
    -0.87
     rağmen
    -0.85
     entweder
    -0.85
    Either
    -0.84
     forskj
    -0.84
    ikkert
    -0.84
    POSITIVE LOGITS
     tasks
    1.32
     task
    1.31
     achieved
    1.30
     priority
    1.23
     mission
    1.16
     paramount
    1.14
     accomplished
    1.11
     goals
    1.09
     requires
    1.08
    tasks
    1.08
    Activations Density 0.111%

    No Known Activations