© 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-16K
    7. 9515
    Prev
    Next
    INDEX
    Explanations

    a plea

    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_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
     )
    1.18
    ↵
    1.12
     computer
    1.02
     classroom
    1.00
     writings
    0.99
     Computers
    0.98
     community
    0.98
     program
    0.97
     Writings
    0.97
     administrator
    0.97
    POSITIVE LOGITS
     noches
    1.20
     canaux
    1.15
     canales
    1.14
    ỷ
    1.13
     galería
    1.10
     espalda
    1.10
    arlight
    1.09
     bloques
    1.09
     inactivació
    1.09
    endela
    1.09
    Activations Density 0.312%

    No Known Activations