© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59340
    Prev
    Next
    INDEX
    Explanations

    code object instantiation

    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
    щении
    -0.75
     blossoms
    -0.73
    批判
    -0.72
     tecnológicos
    -0.72
    uttosto
    -0.70
    mOn
    -0.69
    oreille
    -0.69
     Kranken
    -0.68
     Jewels
    -0.68
    ستخدم
    -0.68
    POSITIVE LOGITS
    calculated
    0.86
     oby
    0.84
     named
    0.84
     obiek
    0.84
    Object
    0.83
     Formel
    0.80
    Group
    0.80
     project
    0.80
    bunda
    0.79
    局面
    0.78
    Activations Density 0.043%

    No Known Activations