© 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. 31-GEMMASCOPE-2-RES-65K
    7. 10782
    Prev
    Next
    INDEX
    Explanations

    without parameters

    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_31_width_65k_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
     particolarmente
    0.46
    土
    0.45
     вигля
    0.44
     aliran
    0.43
    кле
    0.43
     ശ്രമ
    0.42
    Какой
    0.42
    德國
    0.42
    ざ
    0.41
     ஆனால்
    0.41
    POSITIVE LOGITS
    标识
    0.50
    iotensin
    0.49
    ID
    0.47
    it
    0.46
     has
    0.46
    sys
    0.46
    discharge
    0.46
     outsource
    0.46
     discharge
    0.45
     deny
    0.44
    Activations Density 0.002%

    No Known Activations