© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 32555
    Prev
    Next
    INDEX
    Explanations

    configuration and properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasus
    0.53
    -"+
    0.53
     борьбе
    0.53
    '
    0.50
    口座
    0.49
    榱
    0.48
    তেন
    0.47
     Clause
    0.47
     Nieto
    0.47
     ak
    0.46
    POSITIVE LOGITS
    à
    0.55
     vérifier
    0.52
    seems
    0.50
    ين
    0.50
    لة
    0.49
    ২
    0.49
    ά
    0.48
    është
    0.48
    ிகளைக்
    0.48
    ٹری
    0.48
    Activations Density 0.008%

    No Known Activations