© 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. 31-GEMMASCOPE-2-RES-16K
    7. 3977
    Prev
    Next
    INDEX
    Explanations

    На + предлог / начало

    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
    to
    0.70
    at
    0.64
    orch
    0.61
    েরও
    0.60
    ec
    0.59
    责
    0.58
    an
    0.57
    line
    0.57
    于
    0.57
    idx
    0.57
    POSITIVE LOGITS
     základě
    0.75
     terenie
    0.73
     behalf
    0.71
     pewno
    0.70
     meisten
    0.68
     початку
    0.65
     tuto
    0.64
     konci
    0.64
     rynku
    0.64
     początku
    0.63
    Activations Density 0.043%

    No Known Activations