© 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. 109471
    Prev
    Next
    INDEX
    Explanations

    property transfer evidence collection

    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
     ≥
    0.55
    i
    0.53
    ável
    0.52
     согласно
    0.52
    j
    0.50
     може
    0.50
    ument
    0.50
     對
    0.49
     entre
    0.48
    e
    0.48
    POSITIVE LOGITS
    BoolVar
    0.51
    ائرة
    0.48
     IntegerValue
    0.47
     topologically
    0.44
    ChatMessage
    0.44
    தியம்
    0.43
    كي
    0.43
    pq
    0.42
     CommandLine
    0.41
    اليد
    0.41
    Activations Density 0.001%

    No Known Activations