© 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. 241369
    Prev
    Next
    INDEX
    Explanations

    cameras, add, ago, exile, boosted, ologist, stomach, and, middle, friend

    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
    ０
    0.52
     homens
    0.49
     Wikispecies
    0.47
     Irishman
    0.46
     spineItem
    0.46
    ================
    0.46
    offsetWidth
    0.46
    ০
    0.45
    ⁢</
    0.44
     deshalb
    0.44
    POSITIVE LOGITS
    éra
    0.46
    ied
    0.46
    era
    0.46
     والمع
    0.45
    adina
    0.44
     بانک
    0.44
    étés
    0.43
     अम्
    0.42
    illes
    0.42
    oloj
    0.42
    Activations Density 0.000%

    No Known Activations