© 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. 1382
    Prev
    Next
    INDEX
    Explanations

    anime, internet, Chinese, depression

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ل
    0.36
     ainult
    0.34
     tenia
    0.31
     Strip
    0.30
     überprüfen
    0.29
     chromosome
    0.29
     τησ
    0.28
     neutrophil
    0.27
    chrome
    0.27
    ರಿಸ
    0.27
    POSITIVE LOGITS
     throughout
    0.33
    ovin
    0.31
    и
    0.31
    ෞ
    0.31
    作为
    0.31
    ㅡ
    0.30
     thanks
    0.29
    .
    0.29
     буду
    0.29
    作為
    0.29
    Activations Density 0.612%

    No Known Activations