© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 7319
    Prev
    Next
    INDEX
    Explanations

    comfortably hold conversation

    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
    rium
    0.96
    ᄃ
    0.90
     становника
    0.89
     दा
    0.85
     셀
    0.85
    龜
    0.84
    бал
    0.83
    詡
    0.82
    統領
    0.82
     dara
    0.81
    POSITIVE LOGITS
     adalah
    1.17
     είναι
    1.10
     diantaranya
    1.10
    はその
    1.09
     منها
    1.04
     Yunan
    1.04
     ones
    1.00
     ovat
    0.99
    是以
    0.99
     berasal
    0.99
    Activations Density 0.155%

    No Known Activations