© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 13
    Prev
    Next
    INDEX
    Explanations

    'L' words or 'am programmed'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_width_16k_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
    Woods
    0.70
    ◘
    0.69
     Ferguson
    0.69
    风
    0.67
     Wunder
    0.66
    ────
    0.66
     Woods
    0.66
    ouch
    0.64
    Bom
    0.63
     Fujita
    0.63
    POSITIVE LOGITS
     L
    1.90
    L
    1.78
    LIS
    1.69
    Ls
    1.69
     LI
    1.63
    LT
    1.60
    LS
    1.59
     LSP
    1.58
     LS
    1.58
    LLL
    1.58
    Activations Density 15.402%

    No Known Activations