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

    Neuronpedia

    Jacobian LensNEW
    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. 63451
    Prev
    Next
    INDEX
    Explanations

    mathematical calculations

    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
     γίνεται
    0.40
    ယ
    0.40
     Nowhere
    0.39
     αυτή
    0.39
    Also
    0.36
    الله
    0.36
    becomes
    0.35
    ighed
    0.35
     raspberries
    0.34
    CEEDINGS
    0.34
    POSITIVE LOGITS
     togg
    0.36
    uscany
    0.35
     anomaly
    0.34
     minhas
    0.34
     mein
    0.34
    嫔
    0.34
     दूंगा
    0.33
    чик
    0.33
    ผม
    0.33
    िनी
    0.33
    Activations Density 0.071%

    No Known Activations