© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 19433
    Prev
    Next
    INDEX
    Explanations

    engineering components or descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ᱓
    0.57
    lockSeconds
    0.55
     polypes
    0.55
    有名
    0.53
    ற்று
    0.52
    स्‍या
    0.52
     сегодня
    0.52
     noirâtre
    0.51
    扱う
    0.49
    𒌆
    0.49
    POSITIVE LOGITS
    re
    0.64
    c
    0.58
    ↵
    0.53
     Components
    0.51
    s
    0.50
    ’
    0.49
     f
    0.49
     a
    0.48
     Component
    0.48
    per
    0.47
    Activations Density 0.001%

    No Known Activations