© 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. 13640
    Prev
    Next
    INDEX
    Explanations

    improving quickly

    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
    緝
    0.46
     ([
    0.46
     Архивная
    0.46
     這個
    0.45
    lanelet
    0.45
     ("
    0.44
     Fulfillment
    0.43
    ará
    0.43
    شارات
    0.43
     raison
    0.42
    POSITIVE LOGITS
    際に
    0.55
    ش
    0.48
    ی
    0.47
    سے
    0.44
    กว่า
    0.43
    らない
    0.43
    itza
    0.43
     longer
    0.42
     लोकल
    0.42
    中最
    0.41
    Activations Density 0.001%

    No Known Activations