© 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. 229674
    Prev
    Next
    INDEX
    Explanations

    authenticity, analog, scope, felt

    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
    🥉
    0.50
    轂
    0.49
    事が
    0.48
    鑄
    0.46
    <0x9C>
    0.45
    🔰
    0.45
    ಸ್ಯ
    0.44
    ರ್ಯ
    0.44
    セミ
    0.44
    ர்க
    0.44
    POSITIVE LOGITS
     i
    0.51
     city
    0.49
     run
    0.48
     sou
    0.48
     maio
    0.46
     foray
    0.46
     studio
    0.46
     Calais
    0.46
     spotlight
    0.45
     City
    0.45
    Activations Density 0.002%

    No Known Activations