© 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. 12232
    Prev
    Next
    INDEX
    Explanations

    form tag method attribute

    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
     isolamento
    -1.23
    LEBR
    -1.13
     Gesund
    -1.13
     involucra
    -1.13
    groet
    -1.12
     silêncio
    -1.09
     tênis
    -1.08
     also
    -1.08
     pensamento
    -1.06
     emprego
    -1.06
    POSITIVE LOGITS
     and
    1.06
    ższych
    1.02
    socket
    1.00
    submit
    0.99
     hipote
    0.98
     їх
    0.96
     associée
    0.95
    ratos
    0.94
     Villiers
    0.93
     okres
    0.93
    Activations Density 0.001%

    No Known Activations