© 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. 167729
    Prev
    Next
    INDEX
    Explanations

    Eva and Ava names

    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
    нік
    0.41
    джи
    0.40
    мас
    0.39
    軒
    0.38
    стан
    0.38
    Авто
    0.38
     وده
    0.38
    അ
    0.38
    Джек
    0.37
    вит
    0.37
    POSITIVE LOGITS
     constructed
    0.41
    osoever
    0.41
     sop
    0.40
     Seal
    0.40
    ressions
    0.39
     Fig
    0.39
     ribonucle
    0.38
    seal
    0.37
     Ú
    0.36
     ies
    0.36
    Activations Density 0.001%

    No Known Activations