© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 100780
    Prev
    Next
    INDEX
    Explanations

    query type, view of, promise of

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

    words or phrases denoting relationship or role

    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
    Not in Any Lists

    No Comments

    Negative Logits
    主題
    0.52
    長
    0.50
    小さ
    0.50
    Rüyada
    0.48
    陇
    0.47
    长
    0.47
     аба
    0.46
    府
    0.46
     Фила
    0.45
    庇
    0.45
    POSITIVE LOGITS
     aquatic
    0.51
     bilingual
    0.49
     korean
    0.46
     badminton
    0.46
     experiment
    0.45
     blacksmith
    0.45
     mathematical
    0.45
     bilinear
    0.45
     sewers
    0.44
     grammatical
    0.44
    Activations Density 0.000%

    No Known Activations