© 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. 68776
    Prev
    Next
    INDEX
    Explanations

    body and its conditions

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

    price-value comparison

    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
    DEM
    0.45
     thematic
    0.43
    সজ্জিত
    0.41
     بُ
    0.40
     Banquet
    0.40
     修
    0.39
     চৌ
    0.39
    SPRAY
    0.39
    SIGNAL
    0.39
    🎰
    0.39
    POSITIVE LOGITS
    yil
    0.45
    гих
    0.43
    一份
    0.43
     amici
    0.42
     drones
    0.42
    nds
    0.42
    іль
    0.42
    ppers
    0.41
     paramedics
    0.41
    ima
    0.41
    Activations Density 0.001%

    No Known Activations