© 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. 195631
    Prev
    Next
    INDEX
    Explanations

    all rights reserved

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

    parameters and values

    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
    李
    0.45
     VA
    0.43
    别
    0.43
    issenschaft
    0.41
    本地
    0.41
    副本
    0.41
    ອາ
    0.41
     rehe
    0.41
    附近
    0.41
     तहे
    0.41
    POSITIVE LOGITS
    resu
    0.51
    𝐟
    0.48
    Prob
    0.48
    তবে
    0.48
    Ks
    0.47
    nts
    0.47
    plus
    0.46
    urses
    0.46
    Obs
    0.44
    quets
    0.44
    Activations Density 0.001%

    No Known Activations