© 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. 55683
    Prev
    Next
    INDEX
    Explanations

    describing physical attributes or states

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

    looking for total

    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
    Deposito
    0.43
     వీటి
    0.42
    inston
    0.41
     explicado
    0.41
     fabs
    0.40
     ڏ
    0.40
     බ
    0.40
    。
    0.40
    irea
    0.39
    Jika
    0.39
    POSITIVE LOGITS
     ultrast
    0.46
    rogenic
    0.46
     komfort
    0.46
     белару
    0.46
    skine
    0.44
    විය
    0.44
     anh
    0.44
    стати
    0.44
    വിധ
    0.44
    renergic
    0.44
    Activations Density 0.000%

    No Known Activations