Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-65K
    4. 3967
    Prev
    Next
    INDEX
    Explanations

    AI Chatbot disclaimer

    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_65k_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
    ة
    1.26
    া
    1.25
    aç
    1.21
    ת
    1.17
    a
    1.17
    aop
    1.12
    る
    1.09
     deliberations
    1.08
    ा
    1.06
    TAL
    1.06
    POSITIVE LOGITS
    ting
    1.66
    nya
    1.23
    ty
    1.07
    咪
    1.07
    taining
    1.04
    ri
    1.02
    raman
    1.02
    ことができる
    1.00
    ことができます
    1.00
     darn
    0.98
    Activations Density 0.032%

    No Known Activations