© 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. 11435
    Prev
    Next
    INDEX
    Explanations

    people, community, many

    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
    ALLOWED
    -0.90
     там
    -0.90
     heti
    -0.88
     tiet
    -0.86
     bans
    -0.83
     الجلد
    -0.82
    atoto
    -0.81
    radi
    -0.81
     granito
    -0.78
     degeneracy
    -0.77
    POSITIVE LOGITS
     your
    1.21
     community
    1.15
     people
    1.00
     Rät
    0.95
     now
    0.90
     napisał
    0.90
     many
    0.89
     fans
    0.88
     everybody
    0.88
     userDetails
    0.88
    Activations Density 0.025%

    No Known Activations