© 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. 200183
    Prev
    Next
    INDEX
    Explanations

    Psychological Horror

    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
     licences
    0.46
    ونی
    0.43
    知り
    0.42
     Squares
    0.42
    拟
    0.42
     licence
    0.41
    针对
    0.41
     Encyclopedia
    0.41
     ASSOCI
    0.41
    鷸
    0.41
    POSITIVE LOGITS
    l
    0.51
    ý
    0.46
     пробе
    0.45
    neapolis
    0.43
     Neumann
    0.43
    ंनो
    0.43
     terlebih
    0.42
    n
    0.42
    phants
    0.42
    Cornell
    0.41
    Activations Density 0.004%

    No Known Activations