© 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-262K
    7. 14188
    Prev
    Next
    INDEX
    Explanations

    average of various metrics

    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_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
    Average
    1.24
    ي
    1.13
    average
    1.10
    ่
    1.07
     average
    1.06
    ے
    1.04
    ้
    1.00
    i
    0.99
    ियों
    0.96
     Average
    0.94
    POSITIVE LOGITS
    পড়
    1.54
     दर्
    1.42
    值
    1.39
     rainfall
    1.34
     joe
    1.29
    𝘪
    1.28
    값
    1.28
     glandular
    1.28
     pencil
    1.27
    값을
    1.25
    Activations Density 0.028%

    No Known Activations