© 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. 10505
    Prev
    Next
    INDEX
    Explanations

    current level

    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
    DETA
    1.59
    <unused539>
    1.55
    Seconds
    1.55
    NAB
    1.53
    SECONDS
    1.52
    DBG
    1.52
    鈮
    1.51
    स्यों
    1.51
     دقائق
    1.50
    無需簽證
    1.50
    POSITIVE LOGITS
    -
    1.14
     &
    0.93
    /
    0.87
    ler
    0.82
     wie
    0.75
     vive
    0.72
     rim
    0.71
    rite
    0.71
    itar
    0.70
     et
    0.70
    Activations Density 0.084%

    No Known Activations