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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7503
    Prev
    Next
    INDEX
    Explanations

    all-purpose / All-purpose / all-time / All Apps

    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_31_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
    abilidade
    0.60
     রাকাত
    0.58
    odymium
    0.55
     Dore
    0.55
     Dor
    0.54
     berupa
    0.54
     nrows
    0.54
    壮
    0.54
    INES
    0.54
    ování
    0.53
    POSITIVE LOGITS
     All
    0.95
    All
    0.87
     オール
    0.77
     ऑल
    0.75
    purpose
    0.70
     Purpose
    0.68
    Purpose
    0.66
     purpose
    0.64
     occasions
    0.62
     Все
    0.61
    Activations Density 0.082%

    No Known Activations