© 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. 7214
    Prev
    Next
    INDEX
    Explanations

    per unit or category

    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
    a
    0.63
    m
    0.61
    i
    0.57
    ‌های
    0.55
    instellungen
    0.55
    ne
    0.53
    in
    0.52
    ූ
    0.52
    o
    0.51
    t
    0.51
    POSITIVE LOGITS
     einzelnen
    0.60
     capita
    0.57
     einzelne
    0.55
     egyes
    0.54
     jednotliv
    0.53
     वेळी
    0.52
     unit
    0.48
     annum
    0.48
     workday
    0.45
     iteration
    0.44
    Activations Density 0.127%

    No Known Activations