© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 39878
    Prev
    Next
    INDEX
    Explanations

    pattern matching and definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¹.
    0.48
     Bunun
    0.45
    発生
    0.44
     spontaneity
    0.43
     czego
    0.42
     spont
    0.42
     ongel
    0.41
    Ste
    0.41
     ø
    0.40
     onlar
    0.40
    POSITIVE LOGITS
    ו
    0.50
    CLOSED
    0.48
    ל
    0.47
    ร
    0.47
    achtree
    0.46
     لو
    0.45
     שכ
    0.44
     בדי
    0.43
     продукта
    0.43
    সাব
    0.43
    Activations Density 0.002%

    No Known Activations