© 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
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 104320
    Prev
    Next
    INDEX
    Explanations

    truth tables, log cat, Labrador

    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
    ش
    0.65
    ع
    0.62
    ાર્થી
    0.56
     Toutefois
    0.55
    ق
    0.54
     प्रकारचे
    0.54
     இவர்கள்
    0.54
     Ovaj
    0.54
    aunque
    0.53
    ти
    0.52
    POSITIVE LOGITS
    AT
    0.53
    Positive
    0.50
     positive
    0.49
     sees
    0.47
     decal
    0.47
    ベー
    0.47
    コス
    0.47
     at
    0.46
    鹛
    0.46
    Car
    0.46
    Activations Density 0.000%

    No Known Activations