© 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. 15695
    Prev
    Next
    INDEX
    Explanations

    geocaching and outdoor adventure

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

    treasure hunt or escape room

    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
     選
    0.49
    𝔱
    0.48
    |।
    0.46
    kola
    0.46
     patrón
    0.45
    макраты
    0.45
    bandSize
    0.44
    slidesPerView
    0.43
    ☦
    0.42
    inairement
    0.42
    POSITIVE LOGITS
     Beacon
    0.61
     GPS
    0.61
     Hiking
    0.55
     Adventure
    0.54
     Puzzle
    0.53
     gps
    0.53
    Beacon
    0.52
     RFID
    0.51
     Treasure
    0.51
     Squirrel
    0.51
    Activations Density 0.040%

    No Known Activations