© 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. 202432
    Prev
    Next
    INDEX
    Explanations

    Slow Food, shop which, fire which

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

    assigning colors, categories, or 0/1 outputs

    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
     ether
    0.52
     '=',
    0.41
     Ә
    0.40
     Etr
    0.40
    В
    0.40
    '=
    0.40
    gery
    0.40
    ិ
    0.39
     slug
    0.39
    লোক
    0.38
    POSITIVE LOGITS
     protezione
    0.49
    ঘা
    0.47
     creando
    0.47
    ىرى
    0.47
     mappe
    0.47
     artículo
    0.47
     suivie
    0.46
     articolo
    0.46
     décrite
    0.45
     publiée
    0.45
    Activations Density 0.000%

    No Known Activations