© 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. 63399
    Prev
    Next
    INDEX
    Explanations

    positively improving, secular stagnation

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

    comparative statements and classifications

    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
    ount
    0.47
    IS
    0.47
    ृ
    0.46
    ुक
    0.45
    जा
    0.44
    J
    0.44
    urra
    0.44
    की
    0.44
    okol
    0.44
    k
    0.44
    POSITIVE LOGITS
     authentically
    0.49
     સેવા
    0.48
     façon
    0.47
     hospitalized
    0.47
     nueve
    0.47
     continuer
    0.47
     théâtre
    0.47
     continuar
    0.47
     overtly
    0.46
     репре
    0.46
    Activations Density 0.000%

    No Known Activations