© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 82478
    Prev
    Next
    INDEX
    Explanations

    include / function / material

    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_34/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
     Dana
    -0.69
    ⓥ
    -0.68
    жей
    -0.67
    PRECISION
    -0.65
     Sabine
    -0.64
    üdis
    -0.64
     isothermal
    -0.63
    Dana
    -0.63
     Flow
    -0.63
    PvB
    -0.62
    POSITIVE LOGITS
    ITI
    0.69
    !(
    0.69
    Traits
    0.68
    Client
    0.66
    喳
    0.65
    fsch
    0.65
    élien
    0.65
     마
    0.65
    earth
    0.63
     jars
    0.63
    Activations Density 0.092%

    No Known Activations