© 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. 15025
    Prev
    Next
    INDEX
    Explanations

    production environments

    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
    zelfde
    0.97
     masses
    0.90
     topp
    0.90
    槍
    0.89
     하루
    0.87
    枪
    0.87
    راتكم
    0.85
     isso
    0.84
     друзьями
    0.84
    issances
    0.84
    POSITIVE LOGITS
    urator
    1.06
    kang
    1.06
    𐰤
    1.06
    લ
    1.04
     Kaly
    1.03
    ش
    1.03
    퇸
    1.01
     නිෂ්
    1.01
    led
    1.00
    teki
    1.00
    Activations Density 0.001%

    No Known Activations