© 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-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 9332
    Prev
    Next
    INDEX
    Explanations

    links to external websites

    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_17_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
    ه
    1.89
    ely
    1.54
    и
    1.47
    ʟ
    1.43
    אם
    1.40
     এজন্য
    1.37
    YYYY
    1.36
    ≺
    1.31
    ाम
    1.31
    Ра
    1.30
    POSITIVE LOGITS
    cgi
    2.00
    нең
    1.64
     henüz
    1.54
    DTDs
    1.49
    ト
    1.49
    atás
    1.46
    ancji
    1.46
    oyant
    1.44
     отдельные
    1.43
    icionados
    1.43
    Activations Density 0.041%

    No Known Activations