© 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. 711
    Prev
    Next
    INDEX
    Explanations

    car, bottle, account, code, volume

    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
    o
    1.19
    Î
    1.17
    کنندگان
    1.08
    ம்
    1.06
     rush
    1.03
    Trên
    1.03
     (-)
    1.03
     Özellikle
    1.02
    ns
    1.01
    ة
    1.01
    POSITIVE LOGITS
    regation
    1.34
     sư
    1.08
    ень
    1.07
    ствовали
    0.99
     пара
    0.99
     پیسې
    0.97
    omorphism
    0.96
    ferenz
    0.96
    țe
    0.93
    症
    0.92
    Activations Density 0.001%

    No Known Activations