© 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. 129677
    Prev
    Next
    INDEX
    Explanations

    features available here

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

    specific recommendations or preferences

    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
    owała
    0.52
    い
    0.50
    漲
    0.48
    ă
    0.47
    ār
    0.45
    聲
    0.45
    emde
    0.45
    的游戏
    0.45
    飭
    0.45
    مد
    0.45
    POSITIVE LOGITS
     pozit
    0.50
     ALG
    0.50
     UNIT
    0.49
     stature
    0.49
     unity
    0.48
     PARA
    0.48
     FA
    0.47
     CHART
    0.47
     DA
    0.47
     AFP
    0.47
    Activations Density 0.000%

    No Known Activations