© 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. 179452
    Prev
    Next
    INDEX
    Explanations

    waiting and destinations

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

    as you

    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
     তাহাদিগকে
    0.52
    Ava
    0.50
    Aval
    0.48
    Remark
    0.45
    ת
    0.45
    ութ
    0.43
    Cat
    0.43
    Russia
    0.43
     authorisation
    0.43
    Baba
    0.42
    POSITIVE LOGITS
    riages
    0.50
    🗾
    0.48
     maggio
    0.48
     yr
    0.47
     ongeveer
    0.45
     khoảng
    0.44
    ર્મ
    0.44
     Jahr
    0.44
     tropas
    0.44
     jurul
    0.44
    Activations Density 0.001%

    No Known Activations