© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 296
    Prev
    Next
    INDEX
    Explanations

    starts of sentences or informational entries

    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_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
    л
    1.33
    に
    1.15
    taa
    1.14
     Bharti
    1.14
    로
    1.13
    corn
    1.13
    ০০০
    1.11
    chessboard
    1.10
     tras
    1.09
    خدام
    1.08
    POSITIVE LOGITS
    न
    1.25
     суть
    1.12
    នៃការ
    0.98
    년대
    0.96
    ग्विजय
    0.95
     autres
    0.95
     espaces
    0.94
    لم
    0.93
    行った
    0.93
    upiter
    0.92
    Activations Density 0.607%

    No Known Activations