© 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. 31-GEMMASCOPE-2-RES-16K
    4. 14996
    Prev
    Next
    INDEX
    Explanations

    mathematical or programming context

    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
    ادث
    0.71
     luce
    0.67
     aeropuerto
    0.64
    𒅎
    0.63
     Gespräch
    0.63
     sabato
    0.62
     Noi
    0.61
     Teilnahme
    0.61
     molto
    0.61
     Closeup
    0.61
    POSITIVE LOGITS
    and
    0.89
    the
    0.68
    for
    0.68
    (
    0.66
    Sche
    0.65
    of
    0.65
    или
    0.63
    by
    0.61
    vline
    0.60
    {
    0.59
    Activations Density 0.177%

    No Known Activations