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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30859
    Prev
    Next
    INDEX
    Explanations

    operator precedence, expressions, types

    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
     Indore
    -0.81
     clor
    -0.79
    PropertyChanging
    -0.77
    ázka
    -0.76
     premiers
    -0.74
    말
    -0.74
    чны
    -0.73
    覗
    -0.73
     declared
    -0.72
    Disposed
    -0.72
    POSITIVE LOGITS
    preced
    0.85
     Ode
    0.75
     comma
    0.74
     tuviera
    0.74
    Preced
    0.73
     Gul
    0.72
     associating
    0.72
    Opera
    0.70
     preced
    0.69
    Ode
    0.69
    Activations Density 0.010%

    No Known Activations