© 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. 205653
    Prev
    Next
    INDEX
    Explanations

    create advantage

    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
     "/
    0.44
     endereco
    0.44
     Usuario
    0.43
     Xerox
    0.42
    λά
    0.41
     Biblioteca
    0.41
     devoured
    0.41
    ,",
    0.40
     "^
    0.40
     giphy
    0.40
    POSITIVE LOGITS
    古
    0.45
     हाउस
    0.44
    等
    0.44
    ры
    0.44
    يف
    0.43
    <unused2175>
    0.43
    깐
    0.42
    ائ
    0.42
    кс
    0.42
    ukup
    0.42
    Activations Density 0.005%

    No Known Activations