© 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-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-262K
    7. 4265
    Prev
    Next
    INDEX
    Explanations

    who decides

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_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
    ?
    0.31
    ър
    0.29
    similarity
    0.29
     a
    0.27
     Learned
    0.27
     the
    0.27
     describe
    0.26
     ggplot
    0.26
    Пер
    0.26
    ؟
    0.26
    POSITIVE LOGITS
    and
    0.33
     soldi
    0.30
    iyaç
    0.29
    足を
    0.29
    ed
    0.29
     soins
    0.29
    喲
    0.29
    bly
    0.28
     messen
    0.28
     quarts
    0.28
    Activations Density 0.024%

    No Known Activations