© 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. 136241
    Prev
    Next
    INDEX
    Explanations

    image, attribute, fav

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

    positions and roles

    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
     রাষ্ট্রপতি
    0.46
    لقه
    0.45
    尿
    0.45
     करतो
    0.44
     Kampf
    0.44
    ध्यक्ष
    0.42
    دايه
    0.42
    ంబే
    0.41
    中です
    0.41
     Wä
    0.41
    POSITIVE LOGITS
    ન
    0.51
    itr
    0.49
    ot
    0.49
    iton
    0.47
    Image
    0.46
    i
    0.46
    Double
    0.46
    ị
    0.46
     from
    0.45
     -
    0.44
    Activations Density 0.000%

    No Known Activations