© 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. 249981
    Prev
    Next
    INDEX
    Explanations

    my own, day service, automatic formatting

    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
    0.52
     volumen
    0.49
     noi
    0.48
     densidad
    0.48
     cocktail
    0.46
     thunder
    0.46
     besoin
    0.46
    噹
    0.46
     despacho
    0.45
    क्रिया
    0.45
    POSITIVE LOGITS
    に行
    0.48
    xCoordinate
    0.47
     alkalies
    0.47
    xF
    0.46
     поз
    0.46
    xE
    0.46
     있죠
    0.46
    separatedBy
    0.45
    )>\
    0.43
     초기
    0.42
    Activations Density 0.001%

    No Known Activations