© 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. 17-GEMMASCOPE-2-RES-16K
    7. 10635
    Prev
    Next
    INDEX
    Explanations

    Crossword clues and descriptions

    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
     slams
    1.01
    િ
    0.98
    তার
    0.98
     impe
    0.97
    實際
    0.95
    资格
    0.94
     Appro
    0.93
    ती
    0.93
    淹
    0.92
    实践
    0.92
    POSITIVE LOGITS
     Во
    1.20
     colorless
    1.11
    ว่าจะ
    1.09
    %=
    1.08
    jst
    1.05
    กก
    1.05
    hny
    1.05
    ñón
    1.04
    SORT
    1.03
    র্ধ্ব
    1.03
    Activations Density 0.003%

    No Known Activations