© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 205806
    Prev
    Next
    INDEX
    Explanations

    limitations or exceptions

    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
    Negative Logits
     procédés
    0.49
     PlayerSelector
    0.49
     gacchati
    0.48
     continueRoutine
    0.48
     systèmes
    0.47
     parabol
    0.46
     kë
    0.46
    鸴
    0.46
     interni
    0.46
     vacanam
    0.46
    POSITIVE LOGITS
    t
    0.58
    SER
    0.48
    a
    0.46
    d
    0.45
     टू
    0.45
     contagious
    0.45
    state
    0.45
    temperature
    0.44
     जिसने
    0.44
    er
    0.44
    Activations Density 0.001%

    No Known Activations