© 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. 56655
    Prev
    Next
    INDEX
    Explanations

    product names and legal terms

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

    meme template and presentations

    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
    ၊
    0.54
    的国家
    0.51
     Kementerian
    0.49
     Phenomenology
    0.48
     Einstellungen
    0.48
     Agregar
    0.48
     ऊंची
    0.48
     Comando
    0.48
    xAxis
    0.47
     Jeder
    0.47
    POSITIVE LOGITS
     collector
    0.51
    财
    0.47
     possible
    0.46
    財
    0.44
     difícil
    0.43
    بيقات
    0.43
    eh
    0.42
     cheap
    0.42
     repertoire
    0.42
    "—
    0.42
    Activations Density 0.000%

    No Known Activations