© 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. 105387
    Prev
    Next
    INDEX
    Explanations

    ? and game abilities

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

    dimensions and measurements

    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
     அமைந்து
    0.51
    raina
    0.49
     lézards
    0.47
    ECTION
    0.47
     lézard
    0.47
    ﺖ
    0.46
    ینگ
    0.45
     dini
    0.45
    コハマ
    0.45
     azi
    0.45
    POSITIVE LOGITS
     ideas
    0.44
    드가
    0.44
     President
    0.41
     Town
    0.41
    Dry
    0.39
    ቐ
    0.39
     Trudeau
    0.39
     kritik
    0.39
    Which
    0.39
    ষ্ণ
    0.39
    Activations Density 0.002%

    No Known Activations