© 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. 18528
    Prev
    Next
    INDEX
    Explanations

    locations and prevalence

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

    spoken by or in

    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
    ေသ
    0.42
     mince
    0.42
    ('.'
    0.40
    ត្ថ
    0.40
    护
    0.40
    dick
    0.39
     minify
    0.39
     Pellet
    0.39
    柄
    0.38
    ETER
    0.38
    POSITIVE LOGITS
     sayıda
    0.44
     Республика
    0.44
    ங்க்
    0.43
    状態で
    0.42
     zaidi
    0.42
    гу
    0.41
    状態
    0.41
    меч
    0.41
    ‎
    0.41
    場面積
    0.41
    Activations Density 0.000%

    No Known Activations