© 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. 205760
    Prev
    Next
    INDEX
    Explanations

    settings, landscape, display, legal, before, ready

    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
    磡
    0.53
    मताओं
    0.50
    iliśmy
    0.49
    ವುದ
    0.48
    вшая
    0.46
     सभी
    0.46
    त्तर
    0.46
    䀘
    0.46
     हाम्रो
    0.45
     我们
    0.45
    POSITIVE LOGITS
    Date
    0.45
    V
    0.45
    Pour
    0.42
    DateTime
    0.41
    Joe
    0.41
     resist
    0.40
    J
    0.40
    Being
    0.40
    中
    0.40
    Ker
    0.39
    Activations Density 0.007%

    No Known Activations