© 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. 122706
    Prev
    Next
    INDEX
    Explanations

    destruction of the Jews

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

    historical records, often seen, essentially, evolution

    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
    '%(
    0.52
    t
    0.51
    新潟
    0.49
    oC
    0.48
     большим
    0.47
    kada
    0.47
    ગુ
    0.46
    اوی
    0.46
    ﻗ
    0.45
    ിച്ചത്
    0.45
    POSITIVE LOGITS
     आरोपित
    0.45
     Scattering
    0.44
     heretofore
    0.43
     defens
    0.43
     Hunt
    0.42
     superstit
    0.42
     haunt
    0.41
    Saver
    0.41
     स्थानांतरित
    0.41
     Wife
    0.41
    Activations Density 0.001%

    No Known Activations