© 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. 117030
    Prev
    Next
    INDEX
    Explanations

    web server

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

    agregar otro

    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
     robbed
    0.46
    匹
    0.45
     W
    0.45
     AX
    0.45
    盗
    0.44
    同
    0.44
    出血
    0.43
    XO
    0.43
     аналоги
    0.43
    地面
    0.42
    POSITIVE LOGITS
     সময়ে
    0.53
    ფილი
    0.50
    entiti
    0.48
     პროგრამ
    0.47
    ന്ത്രി
    0.47
    algorith
    0.46
     publi
    0.44
     Reactors
    0.44
     gitu
    0.44
    znam
    0.43
    Activations Density 0.001%

    No Known Activations