© 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. 2285
    Prev
    Next
    INDEX
    Explanations

    official founding

    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
    ễ
    0.66
     воздей
    0.65
     flujo
    0.57
     digested
    0.57
     транспорта
    0.57
     kullanarak
    0.57
    }+{
    0.55
    Ễ
    0.55
     диапазо
    0.55
     segítség
    0.54
    POSITIVE LOGITS
     founded
    2.77
     founding
    2.67
     Founded
    2.59
    Founded
    2.48
    founded
    2.30
    创立
    2.22
     founders
    2.20
     설립
    2.20
     Founding
    2.19
     gegründet
    2.16
    Activations Density 0.503%

    No Known Activations