© 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. 185048
    Prev
    Next
    INDEX
    Explanations

    questions starting with can or do

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

    acceleration and velocity

    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
     $
    0.49
     coprodu
    0.46
     $\
    0.45
     plaques
    0.45
     confeder
    0.44
     vibration
    0.44
     collett
    0.44
     sub
    0.43
     jh
    0.42
     perl
    0.42
    POSITIVE LOGITS
    ü
    0.50
    ått
    0.47
    า
    0.46
     істо
    0.46
    віда
    0.46
     endeavoured
    0.46
     विद्यार्थ्या
    0.44
    นุ
    0.44
    ือง
    0.44
    žem
    0.43
    Activations Density 0.001%

    No Known Activations