© 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. 17-GEMMASCOPE-2-RES-16K
    7. 10167
    Prev
    Next
    INDEX
    Explanations

    opening bracket or brace

    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
     hindsight
    1.12
    itories
    1.09
    setlength
    1.09
    ちな
    1.08
    !\!\
    1.07
     discern
    1.06
    𝙖
    1.05
     जिनकी
    1.04
    請問
    1.03
    ₂)
    1.02
    POSITIVE LOGITS
     खाम
    1.19
    ע
    1.08
    生素
    1.08
    电阻
    1.01
    ள்ளது
    1.01
    Ε
    1.01
    ご飯
    0.99
     jardin
    0.99
    Wikimedia
    0.95
    檚
    0.95
    Activations Density 0.001%

    No Known Activations