© 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. 106447
    Prev
    Next
    INDEX
    Explanations

    square scarfcarved marble

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

    cultural traditions and their variations

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ل
    0.50
    л
    0.50
    ได้อย่าง
    0.47
     sérieux
    0.46
    ட்டிக்க
    0.46
     Ruth
    0.45
    妿
    0.45
     গুরুতর
    0.45
    넛
    0.45
     नष्ट
    0.44
    POSITIVE LOGITS
     compartir
    0.54
    lista
    0.45
     dicho
    0.42
     celebrar
    0.41
     市
    0.41
    primir
    0.41
     compañeros
    0.40
     banquet
    0.40
     origin
    0.40
     etiquette
    0.40
    Activations Density 0.001%

    No Known Activations