© 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. 29056
    Prev
    Next
    INDEX
    Explanations

    redirects here

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

    language identification

    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
    atoms
    0.57
    thousand
    0.55
    handle
    0.54
    mask
    0.54
    s
    0.54
    ords
    0.53
    cut
    0.52
    ods
    0.52
    handles
    0.52
    been
    0.51
    POSITIVE LOGITS
    的な
    0.46
     alterar
    0.45
    NU
    0.44
     suono
    0.44
    적인
    0.44
    รวม
    0.44
     fēng
    0.43
     zdję
    0.43
     galería
    0.42
    洺
    0.42
    Activations Density 0.000%

    No Known Activations