© 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. 22-GEMMASCOPE-2-RES-16K
    7. 547
    Prev
    Next
    INDEX
    Explanations

    initialisms and acronyms

    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_22_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
    u
    1.16
    al
    1.16
    in
    1.13
    r
    1.05
    y
    1.05
    er
    1.04
    on
    1.03
    l
    1.01
    و
    0.98
    ar
    0.97
    POSITIVE LOGITS
    UCK
    1.07
    ImgBoard
    1.05
    myCollision
    0.99
    getSaveLocation
    0.98
    embangunan
    0.94
    ӧ
    0.94
     ሽፋን
    0.93
    OTE
    0.92
    ktCap
    0.92
     বাসস্থান
    0.92
    Activations Density 0.635%

    No Known Activations