© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 25229
    Prev
    Next
    INDEX
    Explanations

    common contextual words

    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
    別
    0.54
    自宅
    0.52
    峎
    0.52
    별
    0.49
    fashioned
    0.47
    㹮
    0.47
    是以
    0.46
    手中
    0.46
    㧿
    0.45
     শ্রে
    0.45
    POSITIVE LOGITS
    atik
    0.44
     biz
    0.44
    OY
    0.44
    es
    0.43
     membranes
    0.42
    ese
    0.41
     Unions
    0.40
    iendo
    0.40
     play
    0.39
     Hate
    0.39
    Activations Density 0.006%

    No Known Activations