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-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 7853
    Prev
    Next
    INDEX
    Explanations

    #define directives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_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
    й
    3.15
    ला
    2.81
    м
    2.71
    ل
    2.53
    ف
    2.41
    ن
    2.20
    দ
    2.18
    er
    2.06
    en
    2.05
    ع
    2.04
    POSITIVE LOGITS
    що
    1.96
    slut
    1.94
    ๎
    1.77
    ファスナー
    1.75
    ierend
    1.65
     asa
    1.63
    usion
    1.61
    скохозяй
    1.59
    檛
    1.59
    sinh
    1.59
    Activations Density 0.006%

    No Known Activations