© 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. 52532
    Prev
    Next
    INDEX
    Explanations

    key, class, coagulate

    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
     ammonia
    0.49
     sailboat
    0.49
    ला
    0.48
    preferably
    0.47
    ко
    0.46
    peg
    0.45
     preferably
    0.45
    اموش
    0.45
    س
    0.44
     Ammonia
    0.44
    POSITIVE LOGITS
    Andy
    0.47
     تھی
    0.44
     હતી
    0.43
     публі
    0.43
    Fernando
    0.43
    Business
    0.42
     splike
    0.42
     थी
    0.41
     महत्वपूर्ण
    0.41
    OWA
    0.41
    Activations Density 0.000%

    No Known Activations