© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 2550
    Prev
    Next
    INDEX
    Explanations

    physical actions and direction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_65k_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
    0.91
    p
    0.86
    i
    0.85
    場合は
    0.85
    andez
    0.82
    n
    0.81
    uso
    0.80
     результата
    0.80
    sap
    0.77
     การ
    0.77
    POSITIVE LOGITS
     pulang
    1.23
     경찰
    1.21
     overland
    1.19
     inFile
    1.18
    ன்னி
    1.15
     nervously
    1.12
     피해
    1.12
     alongside
    1.12
     forwarded
    1.12
     슬
    1.11
    Activations Density 0.277%

    No Known Activations