© 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. 52179
    Prev
    Next
    INDEX
    Explanations

    national state concentration settings designs meringue Air line

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

    os.path and foreign characters

    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
    ↵
    0.55
    0.46
     (
    0.42
     for
    0.42
    ↵↵
    0.40
     and
    0.39
    .
    0.39
     Restaurant
    0.37
     Price
    0.36
     College
    0.36
    POSITIVE LOGITS
    Ბ
    0.45
    utérus
    0.44
    ཥ
    0.44
    Კ
    0.43
     ჩატი
    0.42
    Მ
    0.41
    ༧
    0.41
    𝘐
    0.41
    ཋ
    0.41
    Altri
    0.40
    Activations Density 0.020%

    No Known Activations