© 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-65K
    7. 44815
    Prev
    Next
    INDEX
    Explanations

    brief or detailed scope

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ыргыз
    0.45
    optional
    0.43
    avac
    0.42
    ᱘
    0.42
    ']=
    0.42
    op
    0.41
    dom
    0.40
    iven
    0.40
    ajer
    0.40
    ၢ
    0.40
    POSITIVE LOGITS
     تازه
    0.46
     anciens
    0.44
     осень
    0.43
     опыт
    0.43
     ،
    0.42
     종류
    0.42
     observance
    0.42
     중에
    0.42
     چه
    0.42
    初期
    0.42
    Activations Density 0.017%

    No Known Activations