© 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. 12-GEMMASCOPE-2-RES-16K
    7. 2630
    Prev
    Next
    INDEX
    Explanations

    set up

    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_12_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
     Khark
    1.72
     Appellant
    1.59
    $%
    1.47
     subter
    1.40
    сок
    1.39
    স্পতি
    1.38
     %>/
    1.38
     stash
    1.38
     mols
    1.37
    hops
    1.37
    POSITIVE LOGITS
    ts
    2.13
    tting
    2.06
    تی
    1.82
    ્ટ
    1.82
    ف
    1.82
     Außerdem
    1.69
    ı
    1.69
    би
    1.66
     എന്നാല്‍
    1.66
    으면
    1.65
    Activations Density 0.154%

    No Known Activations