© 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. 48200
    Prev
    Next
    INDEX
    Explanations

    shell scripting assignments

    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
    ceno
    -0.73
    ISTOL
    -0.69
    *
    -0.69
     partly
    -0.68
    <h3>
    -0.67
    licó
    -0.65
    厘米
    -0.65
     AutoMapper
    -0.65
    effetto
    -0.65
    личные
    -0.64
    POSITIVE LOGITS
     let
    1.71
    let
    1.34
     lett
    1.24
    =$((
    1.21
    ((
    1.16
    Let
    1.06
     expr
    1.02
    expr
    1.00
    LETT
    0.98
     Let
    0.98
    Activations Density 0.035%

    No Known Activations