© 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. 186119
    Prev
    Next
    INDEX
    Explanations

    nouns followed by context

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

    notifications and chart patterns

    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
     เพราะ
    0.52
     ବି
    0.50
     マル
    0.50
     relev
    0.47
     ප
    0.46
    u
    0.46
     кан
    0.45
    isam
    0.45
    ur
    0.44
     засто
    0.42
    POSITIVE LOGITS
    USR
    0.53
     onshore
    0.49
    दक्षिण
    0.48
    ToGo
    0.47
    ﻱ
    0.47
    BackgroundTask
    0.47
    Poss
    0.46
    OSO
    0.46
    YLE
    0.46
    NERS
    0.46
    Activations Density 0.000%

    No Known Activations