© 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. 61284
    Prev
    Next
    INDEX
    Explanations

    foreign language content

    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
    Not in Any Lists

    No Comments

    Negative Logits
     bert
    0.51
    ular
    0.49
    ib
    0.47
     grunds
    0.47
    ONT
    0.46
    etta
    0.46
     asian
    0.46
    [{}\
    0.46
    亞洲
    0.46
    
    0.45
    POSITIVE LOGITS
    我就
    0.44
     recourse
    0.44
     Sito
    0.44
     Secondo
    0.43
    ากร
    0.43
    стояние
    0.42
    comando
    0.42
    ג
    0.41
    νομ
    0.40
    ো
    0.40
    Activations Density 0.003%

    No Known Activations