© 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. 1252
    Prev
    Next
    INDEX
    Explanations

    recursion, resolution, restrictions

    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
     a
    0.40
    ্বরূপ
    0.28
    ’
    0.26
     ofApp
    0.25
     of
    0.23
     SQLException
    0.23
     Critique
    0.23
    A
    0.23
     Catholicism
    0.23
     synthesizing
    0.23
    POSITIVE LOGITS
     squre
    0.32
    ד
    0.30
    и
    0.29
    oum
    0.28
    у
    0.28
    ुत
    0.28
     exib
    0.27
     aprox
    0.27
    ड
    0.27
     बच्चो
    0.27
    Activations Density 0.053%

    No Known Activations