© 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. 115422
    Prev
    Next
    INDEX
    Explanations

    readers finding

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

    explaining or elaborating

    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
    ’
    0.49
    0.46
    quint
    0.44
     अनुबंध
    0.43
    trump
    0.42
     ਮ
    0.42
    funcion
    0.41
    ϭ
    0.41
     NEED
    0.41
    made
    0.40
    POSITIVE LOGITS
    자와
    0.53
    ьер
    0.52
    imizi
    0.50
    暏
    0.50
     alır
    0.49
    椁
    0.49
    اضره
    0.48
     birdseye
    0.48
    ımızı
    0.47
     және
    0.47
    Activations Density 0.001%

    No Known Activations