© 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. 12203
    Prev
    Next
    INDEX
    Explanations

    list items starting with numbers or bullets

    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
     plafon
    -2.58
     siè
    -2.48
     célè
    -2.39
     estadounid
    -2.36
     inond
    -2.31
     meub
    -2.28
     organik
    -2.22
     coreano
    -2.20
     attente
    -2.17
     広場
    -2.14
    POSITIVE LOGITS
     other
    2.50
     not
    2.41
     to
    2.23
     how
    2.23
     actually
    2.11
     A
    2.08
     more
    2.06
     M
    2.03
     get
    2.02
     additional
    2.02
    Activations Density 0.008%

    No Known Activations