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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 7375
    Prev
    Next
    INDEX
    Explanations

    Yahoo Mail, None yet

    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
    ת
    4.05
    ي
    3.88
    ة
    3.48
    ed
    3.11
    e
    3.03
    es
    3.01
    ب
    2.97
    ه
    2.86
    т
    2.81
    tir
    2.76
    POSITIVE LOGITS
    р
    2.28
    ર
    2.28
    illum
    2.22
    δήποτε
    2.20
    𝓌
    2.08
    coords
    2.06
    ਰ
    1.99
    ği
    1.98
    ricted
    1.96
    acle
    1.96
    Activations Density 0.139%

    No Known Activations