© 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. 40-GEMMASCOPE-2-RES-262K
    7. 214630
    Prev
    Next
    INDEX
    Explanations

    vitamins and technical terms

    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
    PhCH
    0.46
    ྟ
    0.39
    uw
    0.38
     että
    0.38
     WK
    0.38
     Carls
    0.36
     Wnd
    0.36
     клетки
    0.36
    ʃ
    0.36
     bahwa
    0.35
    POSITIVE LOGITS
    subcategory
    0.40
     అత్య
    0.39
    ESE
    0.38
     consegu
    0.37
     Absatz
    0.36
    کین
    0.35
    codone
    0.35
    ческом
    0.34
    িজে
    0.34
     သည်
    0.34
    Activations Density 0.045%

    No Known Activations