© 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. 222720
    Prev
    Next
    INDEX
    Explanations

    specialized terms or items

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

    description of items and actions

    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
    that
    0.47
    ๔
    0.46
    wanted
    0.46
    ambilan
    0.46
    ऍ
    0.46
    ωσ
    0.45
    unov
    0.45
    وب
    0.45
    왤
    0.45
    4
    0.44
    POSITIVE LOGITS
     Durable
    0.52
     způso
    0.50
     odborn
    0.49
     Eternity
    0.49
     cały
    0.49
     número
    0.48
     organizado
    0.48
     produziert
    0.48
     jednost
    0.48
     Spacer
    0.48
    Activations Density 0.001%

    No Known Activations