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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 56926
    Prev
    Next
    INDEX
    Explanations

    Formatting, Plastic, Farm, images, or how-to contexts

    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
    ate
    0.50
     Guatemala
    0.45
    ത്തിനു
    0.45
    rology
    0.45
     Nationalism
    0.43
     E
    0.43
     Is
    0.43
    torrent
    0.42
     Chatter
    0.41
     Crocodile
    0.41
    POSITIVE LOGITS
     οικο
    0.54
    আমার
    0.49
     sma
    0.49
     categorically
    0.48
     zwią
    0.47
     zabez
    0.47
    <0xDC>
    0.47
     брен
    0.47
     κά
    0.46
    मुझे
    0.46
    Activations Density 0.010%

    No Known Activations