© 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. 186305
    Prev
    Next
    INDEX
    Explanations

    herb spiral

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

    specific formatting and lists

    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
    পাল
    0.50
    ξ
    0.45
    stellar
    0.43
     अगली
    0.43
     excision
    0.42
     сильно
    0.41
    enz
    0.40
     ಮಾರ
    0.40
    梶
    0.40
    少なくとも
    0.39
    POSITIVE LOGITS
     admins
    0.49
    âche
    0.49
    .';
    0.48
     ንጥረ
    0.47
     rétréc
    0.45
     букмекерлик
    0.45
     cendré
    0.44
     BVHTree
    0.43
     dí
    0.43
     prépuce
    0.43
    Activations Density 0.001%

    No Known Activations