© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 33845
    Prev
    Next
    INDEX
    Explanations

    Elohim"}, {"neighboring"}, {"mobile"}, {"Model"}, {"File"}, {"mass"}, {"varn"}

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    贰章
    0.44
    ﻹ
    0.44
    纨
    0.43
     conduire
    0.41
    ัพ
    0.40
     famil
    0.40
    ያዎች
    0.39
    偣
    0.39
    とに
    0.39
    ProjectType
    0.39
    POSITIVE LOGITS
     mass
    0.46
    sil
    0.44
    Factories
    0.44
    mass
    0.40
     mobile
    0.39
     varn
    0.39
    era
    0.38
    haria
    0.38
     موج
    0.38
    স্পতি
    0.37
    Activations Density 0.000%

    No Known Activations