© 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. 90845
    Prev
    Next
    INDEX
    Explanations

    purchase and activation agreements

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

    official documentation

    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
     хотел
    0.55
    hôtel
    0.51
     хотела
    0.51
    ამის
    0.50
     были
    0.45
     хотят
    0.45
     ሙ
    0.44
    няют
    0.44
     zostały
    0.43
    しています
    0.43
    POSITIVE LOGITS
    瘓
    0.46
     შორის
    0.44
     samoz
    0.41
     valori
    0.41
     acela
    0.41
     minimalistic
    0.41
    值的
    0.40
     Eigent
    0.40
     Whale
    0.40
     ebenso
    0.39
    Activations Density 0.003%

    No Known Activations