© 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. 102970
    Prev
    Next
    INDEX
    Explanations

    noun + preposition

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

    based on

    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
     Characteristics
    0.45
     Melinda
    0.41
     Frye
    0.40
     alluvial
    0.40
     troubled
    0.39
    HAO
    0.39
    詬
    0.38
     Sirius
    0.38
     Carmichael
    0.38
     characteristics
    0.37
    POSITIVE LOGITS
    ósticos
    0.49
    ᠴ
    0.49
    encer
    0.46
    还不
    0.46
    ücken
    0.44
     измере
    0.44
     рекорд
    0.44
    ież
    0.43
     расчета
    0.43
    ui
    0.43
    Activations Density 0.001%

    No Known Activations