© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 173237
    Prev
    Next
    INDEX
    Explanations

    geographic markers and food

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

    displays results

    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
    WATER
    0.50
    AMO
    0.46
    다라고
    0.44
    LESS
    0.43
    challenged
    0.42
    Pup
    0.41
    EMPLOY
    0.41
    y
    0.41
    다
    0.41
    below
    0.41
    POSITIVE LOGITS
     prophecies
    0.46
    ص
    0.44
     recetas
    0.42
    iliz
    0.41
     factories
    0.41
     comprar
    0.41
     resistentes
    0.41
     onshore
    0.41
     fáb
    0.40
    朝
    0.40
    Activations Density 0.001%

    No Known Activations