© 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. 40-GEMMASCOPE-2-RES-262K
    7. 222392
    Prev
    Next
    INDEX
    Explanations

    energy and entropy

    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_40_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
    etsa
    0.43
     gestures
    0.40
    辐
    0.40
     घरवालों
    0.39
    ьому
    0.38
     Rxa
    0.38
     बिहारी
    0.37
     parked
    0.37
    はその
    0.36
    trunk
    0.36
    POSITIVE LOGITS
    faceted
    0.44
     කැ
    0.40
     gloria
    0.38
     rozší
    0.38
    
    0.38
    庿
    0.38
    又有
    0.37
    是有
    0.37
    klar
    0.36
     भु
    0.35
    Activations Density 0.000%

    No Known Activations