© 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. 9-GEMMASCOPE-2-RES-262K
    4. 8417
    Prev
    Next
    INDEX
    Explanations

    role and rules

    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_262k_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
     edgecolor
    1.29
    ᴍ
    1.23
    ге
    1.18
    ाने
    1.15
     unm
    1.13
     eva
    1.13
    analyzer
    1.12
    ᴘ
    1.10
    حر
    1.08
    ருங்க
    1.07
    POSITIVE LOGITS
    स्पति
    1.23
    一个
    1.18
    n
    1.18
    ings
    1.17
    meng
    1.17
     použití
    1.17
    BDT
    1.17
     slechts
    1.17
    acetic
    1.15
    欄
    1.13
    Activations Density 0.000%

    No Known Activations