© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 192583
    Prev
    Next
    INDEX
    Explanations

    art, design, and specific items

    np_acts-logits-general · gemini-2.5-flash-lite

    legal culpability, responsibility, identity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ње
    0.55
    ્રે
    0.52
    ຈັດ
    0.50
    ()}>
    0.49
    jem
    0.49
    FORCE
    0.49
    쪄
    0.48
    тари
    0.48
    ເຕ
    0.48
    စ
    0.47
    POSITIVE LOGITS
     Peut
    0.46
     Gogh
    0.45
     Sergeant
    0.44
     Batik
    0.43
     Mustang
    0.43
     anglers
    0.42
     Est
    0.42
     Ging
    0.41
     Improvements
    0.41
     võivad
    0.41
    Activations Density 0.001%

    No Known Activations