© 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. 1234
    Prev
    Next
    INDEX
    Explanations

    earned muscle

    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
     literal
    1.86
     censure
    1.68
     determinados
    1.67
     cá
    1.60
     seguida
    1.60
     siglas
    1.60
    峙
    1.59
     segundos
    1.57
     secretos
    1.57
    ESTIC
    1.56
    POSITIVE LOGITS
    rao
    1.51
    <0x80>
    1.49
     Chang
    1.28
    rer
    1.27
    lux
    1.27
    pacific
    1.26
    ui
    1.26
     av
    1.24
     chang
    1.24
    neo
    1.22
    Activations Density 0.000%

    No Known Activations