© 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. 9-GEMMASCOPE-2-RES-16K
    7. 30
    Prev
    Next
    INDEX
    Explanations

    2023

    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_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
    y
    2.13
    on
    1.78
    t
    1.70
    al
    1.69
    h
    1.65
    o
    1.58
    िंग
    1.48
    d
    1.43
    ا
    1.42
    textContent
    1.40
    POSITIVE LOGITS
    ित
    1.65
     inboard
    1.55
     Lankan
    1.47
    אים
    1.46
    핌
    1.45
     garland
    1.42
     jungen
    1.42
    🙏🙏
    1.39
     tastefully
    1.35
     rheumatoid
    1.35
    Activations Density 0.142%

    No Known Activations