© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 17486
    Prev
    Next
    INDEX
    Explanations

    match and fit

    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_65k_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
     secretaria
    0.64
    tional
    0.56
    畂
    0.55
     asistente
    0.55
     intranet
    0.54
    తర
    0.53
     întreb
    0.53
     intimid
    0.52
     pertinent
    0.52
     ڪرڻ
    0.52
    POSITIVE LOGITS
    ،
    0.92
     fit
    0.81
    ，
    0.78
     fits
    0.72
    fit
    0.71
    fits
    0.70
    д
    0.70
    ра
    0.70
     Fit
    0.68
    خ
    0.65
    Activations Density 0.067%

    No Known Activations