© 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. 1260
    Prev
    Next
    INDEX
    Explanations

    list items after period or asterisk

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

    key, variables, OR, export, onion, Embed

    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
    ربعة
    0.41
     पार्श्व
    0.40
     ~
    0.39
     waning
    0.37
     vorne
    0.37
    ADD
    0.35
    ன்கள்
    0.35
     মাধ্য
    0.35
    砂糖
    0.35
     atributos
    0.35
    POSITIVE LOGITS
    arlı
    0.41
    ష్య
    0.39
    જી
    0.38
    obed
    0.36
    jších
    0.36
    缉
    0.35
    orious
    0.35
     તૈયાર
    0.35
    arów
    0.35
     Infrared
    0.34
    Activations Density 0.000%

    No Known Activations