© 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. 139487
    Prev
    Next
    INDEX
    Explanations

    news updates, then soon, roof deck, completed, oral

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

    standard, newer, or currently used systems

    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
    CORD
    0.51
    ेंसिल
    0.51
    вели
    0.50
    хо
    0.49
    망
    0.49
    ГУ
    0.48
    装備
    0.47
    하고
    0.47
    钺
    0.46
    කි
    0.46
    POSITIVE LOGITS
     upon
    0.47
     froth
    0.46
     setelah
    0.46
    觡
    0.46
    ματος
    0.45
     allergens
    0.44
     redness
    0.44
     thawed
    0.44
    ubh
    0.44
     recipients
    0.43
    Activations Density 0.000%

    No Known Activations