© 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-16K
    7. 11564
    Prev
    Next
    INDEX
    Explanations

    fractions or division operations

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

    fractions and formulas

    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_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    вича
    0.50
    اف
    0.48
    و
    0.46
     돈
    0.46
    Registre
    0.44
    实话
    0.43
    licts
    0.43
    Пе
    0.42
    珮
    0.42
     marginRight
    0.42
    POSITIVE LOGITS
    তা
    0.46
     بنائیں
    0.44
     established
    0.41
     semiconductor
    0.41
    hline
    0.40
    established
    0.40
     Ehrlich
    0.40
    ok
    0.40
    atau
    0.39
     ASEAN
    0.39
    Activations Density 0.014%

    No Known Activations