© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 14255
    Prev
    Next
    INDEX
    Explanations

    specific entities and states

    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
     nombreux
    1.03
     様
    1.03
    annya
    1.01
     numerosos
    1.00
     carga
    0.99
    뎌
    0.95
     nombreuses
    0.95
     pò
    0.94
    çe
    0.94
    ણને
    0.93
    POSITIVE LOGITS
     Stephens
    1.27
     TRS
    1.23
     Perr
    1.20
     Emery
    1.18
     Loz
    1.17
    ■
    1.16
    幷
    1.16
    orting
    1.16
     EG
    1.15
    RS
    1.14
    Activations Density 0.000%

    No Known Activations