© 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. 38570
    Prev
    Next
    INDEX
    Explanations

    recited wherein claim

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

    within phrases

    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
     Whyte
    0.47
    ادس
    0.44
     Counsel
    0.43
     have
    0.43
    Tutorial
    0.43
     for
    0.43
     సూ
    0.42
    :
    0.41
     Bou
    0.40
     چی
    0.40
    POSITIVE LOGITS
     Patrimonio
    0.50
     aprobado
    0.46
    HOBBIT
    0.46
     demás
    0.46
    ्रोत
    0.46
     realizaron
    0.46
     variedad
    0.46
     thefe
    0.45
     preço
    0.45
    Ζ
    0.45
    Activations Density 0.000%

    No Known Activations