© 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. 29260
    Prev
    Next
    INDEX
    Explanations

    Receive calls, faxes, mail

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

    Garlic Parmesan flavor

    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
     a
    0.41
     Hirsch
    0.41
     historical
    0.39
    жээ
    0.38
     world
    0.38
     Horses
    0.38
     heel
    0.38
     veterinarian
    0.38
     linger
    0.38
     traditional
    0.38
    POSITIVE LOGITS
    ٣
    0.55
    ੩
    0.50
     sottoline
    0.49
     probabilmente
    0.48
    grapes
    0.47
     possibles
    0.47
     provavelmente
    0.46
    imonials
    0.46
     contatt
    0.45
    📩
    0.45
    Activations Density 0.000%

    No Known Activations