© 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. 235519
    Prev
    Next
    INDEX
    Explanations

    camera with features

    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
     classic
    0.46
     subspaces
    0.43
    বাদী
    0.43
     concatenate
    0.41
     voisines
    0.39
    izaciones
    0.39
    숯
    0.39
     leftmost
    0.38
    決して
    0.38
     bluntly
    0.38
    POSITIVE LOGITS
    🔍
    0.54
    Ṣ
    0.52
    et
    0.50
    needed
    0.48
    Cube
    0.48
     Steep
    0.47
    া
    0.47
    required
    0.47
    🏃
    0.47
    🚂
    0.47
    Activations Density 0.001%

    No Known Activations