© 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. 218705
    Prev
    Next
    INDEX
    Explanations

    dear children

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

    options, super, unreliable, encouraging, maintenance

    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
    гент
    0.51
    鎌
    0.49
    куляр
    0.48
    詮
    0.48
    饲
    0.47
    拇
    0.47
    хать
    0.46
     چکے
    0.45
    镙
    0.44
    чно
    0.44
    POSITIVE LOGITS
     LAS
    0.63
    ure
    0.56
     SYSTEM
    0.53
     システム
    0.52
    qu
    0.52
    im
    0.51
     horizontally
    0.51
    mas
    0.50
    ilim
    0.50
    ystem
    0.50
    Activations Density 0.000%

    No Known Activations