© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 209183
    Prev
    Next
    INDEX
    Explanations

    multilingual content

    np_acts-logits-general · gemini-2.5-flash-lite

    improved coverage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     επίσης
    0.49
    |.|
    0.49
    ுகள்
    0.49
    мін
    0.47
     automobil
    0.46
    桔
    0.45
    汽车
    0.45
    ໃຫ້
    0.44
     IMPORTANT
    0.44
     Voiture
    0.44
    POSITIVE LOGITS
    em
    0.47
    ште
    0.45
    в
    0.45
    š
    0.44
    нг
    0.43
    ش
    0.42
    м
    0.41
    да
    0.41
    ра
    0.40
    کس
    0.40
    Activations Density 0.001%

    No Known Activations