© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 10052
    Prev
    Next
    INDEX
    Explanations

    Winklevoss, Wallace, WSO2 IS, Wiley & Sons

    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_22_width_16k_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
    லீ
    0.67
    ɠ
    0.67
     patches
    0.65
     patch
    0.61
     indigenous
    0.60
     tolerated
    0.60
    orphic
    0.60
     pooled
    0.59
     mustered
    0.59
    유
    0.58
    POSITIVE LOGITS
     WO
    1.01
    WO
    0.97
    पों
    0.95
     Wo
    0.94
     WJ
    0.94
    Wo
    0.90
    WM
    0.89
    डब्ल्यू
    0.86
    OW
    0.84
     WT
    0.84
    Activations Density 0.197%

    No Known Activations