© 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. 183160
    Prev
    Next
    INDEX
    Explanations

    next course, free up

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

    increase / decrease / improve

    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
     lassen
    0.49
    <0x97>
    0.47
     pute
    0.46
     može
    0.46
    答案
    0.45
     kræ
    0.44
    尋
    0.44
     Paar
    0.43
    簧
    0.43
     snad
    0.43
    POSITIVE LOGITS
    ipfs
    0.51
    rast
    0.48
    ano
    0.45
    orylation
    0.45
    ➹
    0.45
    osin
    0.44
    nD
    0.44
    Prefs
    0.44
    igamma
    0.44
    ajout
    0.44
    Activations Density 0.000%

    No Known Activations