© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 126585
    Prev
    Next
    INDEX
    Explanations

    OFF or ON

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_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
     terakhir
    0.58
     d
    0.55
     of
    0.50
     Gegen
    0.49
     alchemy
    0.46
    d
    0.46
     transm
    0.46
     German
    0.46
     and
    0.46
     dike
    0.45
    POSITIVE LOGITS
    állítás
    0.44
     lézard
    0.42
    Зна
    0.41
    #![
    0.41
    唓
    0.41
    thisStudent
    0.40
    Highlight
    0.40
    坴
    0.40
    pez
    0.39
    olocation
    0.39
    Activations Density 0.006%

    No Known Activations