© 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. 48676
    Prev
    Next
    INDEX
    Explanations

    lever, leverage, leven, levator

    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
    Broad
    -0.72
     Jurist
    -0.72
    کا
    -0.71
     Hartmann
    -0.71
     broadening
    -0.70
    Де
    -0.68
     Yus
    -0.68
    jak
    -0.68
    joner
    -0.68
     Broad
    -0.67
    POSITIVE LOGITS
    cution
    0.92
     cringe
    0.83
    ancier
    0.80
     clocks
    0.78
    Enzo
    0.78
     Clock
    0.75
    AGED
    0.74
     action
    0.74
    λους
    0.73
    dragons
    0.72
    Activations Density 0.036%

    No Known Activations