© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-16K
    4. 15301
    Prev
    Next
    INDEX
    Explanations

    best suits / further exacerbate

    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
     dàng
    1.33
    ‌و
    1.30
    kanie
    1.23
     unthinkable
    1.22
    ው
    1.22
    무
    1.20
    ⿱
    1.20
    灯
    1.20
    ్ఞ
    1.19
    EOUS
    1.19
    POSITIVE LOGITS
    ির
    1.70
    c
    1.63
    to
    1.57
    could
    1.48
    t
    1.40
    gives
    1.38
    is
    1.36
     GHz
    1.36
     esperaba
    1.32
     составляет
    1.30
    Activations Density 0.196%

    No Known Activations