© 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. 68384
    Prev
    Next
    INDEX
    Explanations

    features

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

    data persistence

    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
     なる
    0.57
     両
    0.52
     ಪ್ರಾರಂಭ
    0.50
     ც
    0.49
    来た
    0.49
     በእ
    0.48
     久
    0.48
    gangenheit
    0.47
    generating
    0.47
    uttu
    0.46
    POSITIVE LOGITS
     Denim
    0.53
     Blockchain
    0.49
     Dubai
    0.46
    blockchain
    0.44
     motorway
    0.43
    बॉलीवुड
    0.42
     denim
    0.41
    媺
    0.41
    فهام
    0.41
     Mundial
    0.41
    Activations Density 0.002%

    No Known Activations