© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11395
    Prev
    Next
    INDEX
    Explanations

    adjusting items and systems

    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
     Hva
    -1.20
     χρήση
    -1.02
     Når
    -1.02
     micrófono
    -1.00
     panneaux
    -1.00
    ingual
    -0.98
     poches
    -0.98
    Lancaster
    -0.97
     Statt
    -0.97
     Lorsqu
    -0.96
    POSITIVE LOGITS
     to
    2.22
     accordingly
    1.66
     adjusts
    1.48
     according
    1.30
     adjusted
    1.30
     adjust
    1.24
     towards
    1.20
     adjusting
    1.20
     toward
    1.19
     the
    1.14
    Activations Density 0.038%

    No Known Activations