© 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. 16-GEMMASCOPE-2-RES-262K
    7. 138174
    Prev
    Next
    INDEX
    Explanations

    chemical suffixes and proper nouns

    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_16_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
    Types
    0.58
    Integr
    0.56
    İ
    0.54
    Controls
    0.54
    层
    0.54
    itä
    0.52
    V
    0.52
    傥
    0.52
     يتم
    0.51
    으면
    0.50
    POSITIVE LOGITS
     contaminate
    0.62
    ט
    0.62
    </h5>
    0.61
    ટ
    0.61
     pregnant
    0.59
     adenocarcinoma
    0.57
    ã
    0.55
     chats
    0.54
     gospodar
    0.54
     maig
    0.54
    Activations Density 0.000%

    No Known Activations