© 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. 224541
    Prev
    Next
    INDEX
    Explanations

    composed, plant, basement, murdered, renovate

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

    categories and classifications

    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
    ()?
    0.49
    ધ
    0.48
    noise
    0.46
    周囲
    0.46
    conver
    0.45
    총
    0.45
    clothes
    0.45
    받
    0.45
    combo
    0.45
    ध्द
    0.44
    POSITIVE LOGITS
     dusted
    0.53
    الية
    0.49
     categoría
    0.47
     sediments
    0.46
     desks
    0.46
     качественно
    0.46
     émissions
    0.45
     hogares
    0.44
     kategori
    0.44
     categorías
    0.44
    Activations Density 0.000%

    No Known Activations