© 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. 64567
    Prev
    Next
    INDEX
    Explanations

    worth noting

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

    automations and states

    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
     hydrate
    0.51
     ∈
    0.50
     concatenate
    0.50
     belong
    0.48
     correspondence
    0.46
    ស់
    0.46
     centralized
    0.46
    າກ
    0.45
     neoplastic
    0.45
    Bb
    0.44
    POSITIVE LOGITS
    স্তার
    0.47
    จัย
    0.47
    ^{*}$-
    0.47
    زی
    0.46
    ARRIVAL
    0.46
    Rajas
    0.46
    媧
    0.45
     উপর
    0.45
     прибы
    0.45
    স্তা
    0.44
    Activations Density 0.000%

    No Known Activations