© 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. 5905
    Prev
    Next
    INDEX
    Explanations

    prompt stream and crucial limits

    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
     Traffic
    0.46
    כים
    0.44
     Bhand
    0.44
    kaya
    0.40
     Yao
    0.40
     overloaded
    0.39
     Energ
    0.39
    倚
    0.39
     UIImage
    0.39
     Idani
    0.39
    POSITIVE LOGITS
    program
    0.50
    ap
    0.48
     Мен
    0.48
     Са
    0.47
    ர்ப
    0.47
    ain
    0.46
    ва
    0.44
    iza
    0.43
     préférences
    0.43
     ব্যব
    0.42
    Activations Density 0.014%

    No Known Activations