Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 124817
    Prev
    Next
    INDEX
    Explanations

    Spirituality, Insertion, Playing

    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
    峴
    0.50
    モ
    0.50
    মো
    0.49
    FILE
    0.48
    GH
    0.48
    Typ
    0.47
    बिट
    0.47
    Ist
    0.46
     proprietà
    0.45
    뷁
    0.45
    POSITIVE LOGITS
     கொடு
    0.46
     devotes
    0.46
     adheres
    0.44
     tận
    0.42
     కొన
    0.42
    anha
    0.41
    có
    0.41
     الن
    0.41
    outlined
    0.41
    translations
    0.41
    Activations Density 0.005%

    No Known Activations