© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 235116
    Prev
    Next
    INDEX
    Explanations

    body parts, physical features, or objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    褸
    0.52
     raced
    0.48
     heeft
    0.46
     și
    0.45
     proporcionar
    0.44
    褛
    0.44
     be
    0.42
    ÇA
    0.42
     şi
    0.42
    تال
    0.42
    POSITIVE LOGITS
     ovaries
    0.50
     quarries
    0.48
     predictors
    0.48
     nostrils
    0.47
     knobs
    0.46
     otherworldly
    0.46
     outcrops
    0.45
     sculptures
    0.45
     spasms
    0.44
     instability
    0.44
    Activations Density 0.000%

    No Known Activations