© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 10756
    Prev
    Next
    INDEX
    Explanations

    do so

    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_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
     puno
    0.70
     ஆகிய
    0.66
    𝗠
    0.65
     spune
    0.64
     definitely
    0.64
    <unused2139>
    0.63
    غان
    0.63
    ഘോഷ
    0.62
     responseObject
    0.62
    揾
    0.62
    POSITIVE LOGITS
     so
    5.70
    so
    4.21
    So
    3.97
     So
    3.81
     så
    3.44
     socalled
    3.44
     soooo
    3.35
     sooo
    3.23
     так
    3.11
    如此
    3.10
    Activations Density 0.077%

    No Known Activations