© 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. 182438
    Prev
    Next
    INDEX
    Explanations

    underneath it all a thinga coupleauthentic treasure

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

    listing multiples

    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
    pero
    0.49
    pert
    0.48
    ree
    0.48
    টি
    0.48
    marketplace
    0.46
    ara
    0.46
    ร้อง
    0.45
    j
    0.44
    But
    0.44
    ere
    0.43
    POSITIVE LOGITS
     Ueda
    0.47
     nooit
    0.47
    ಿಸುತ್ತದೆ
    0.47
     있도록
    0.46
    agricult
    0.45
    ナット
    0.44
    ož
    0.44
    ॲ
    0.44
     തുടങ്ങി
    0.43
     ရက်
    0.42
    Activations Density 0.002%

    No Known Activations