© 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. 28975
    Prev
    Next
    INDEX
    Explanations

    common phrases and sequences

    np_acts-logits-general · gemini-2.5-flash-lite

    basal ganglia, habit formation

    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
    ne
    0.56
     Metabolism
    0.55
    ve
    0.52
    j
    0.50
     Inequality
    0.50
    g
    0.48
    on
    0.48
    ob
    0.48
    ap
    0.47
     Metabolic
    0.47
    POSITIVE LOGITS
     hatchery
    0.49
     antennae
    0.49
     spines
    0.48
     petición
    0.48
    ଟି
    0.47
     poppy
    0.47
    করিয়
    0.47
    িয়৷
    0.46
     кей
    0.46
     intermediaries
    0.46
    Activations Density 0.000%

    No Known Activations