© 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. 167648
    Prev
    Next
    INDEX
    Explanations

    used meth

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

    JAM decisions sarcastic

    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
     liht
    0.56
    -//
    0.53
     malls
    0.52
     boulders
    0.50
     hsize
    0.50
    やか
    0.50
     Clarendon
    0.50
    帳に追加
    0.49
     резер
    0.49
    .//
    0.49
    POSITIVE LOGITS
    en
    0.50
    م
    0.50
    м
    0.48
    و
    0.48
    }=\
    0.47
     Z
    0.46
    ز
    0.45
    ales
    0.44
    um
    0.44
    G
    0.43
    Activations Density 0.000%

    No Known Activations