© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 91317
    Prev
    Next
    INDEX
    Explanations

    explanation of code

    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_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
     בא
    0.47
    Nigeria
    0.45
     قر
    0.44
    英语
    0.43
    汉语
    0.43
    ಲಿಲ್ಲ
    0.43
    ບ
    0.43
    🇸
    0.43
     Из
    0.42
    рави
    0.42
    POSITIVE LOGITS
     dietro
    0.44
     injunction
    0.43
     εμπ
    0.42
     concetto
    0.42
     kangaroo
    0.42
     концеп
    0.41
     dimensioni
    0.40
     τότε
    0.40
     gehe
    0.40
     schematic
    0.39
    Activations Density 0.002%

    No Known Activations