© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 9349
    Prev
    Next
    INDEX
    Explanations

    html tags with digits

    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
    дали
    1.18
    1.14
     EDIT
    1.14
     Editors
    1.12
    archi
    1.09
     Approval
    1.07
     (
    1.03
     study
    1.02
     /
    1.00
     need
    1.00
    POSITIVE LOGITS
    purecounter
    1.66
    <unused119>
    1.64
    <unused629>
    1.63
    <unused44>
    1.62
    <unused1629>
    1.61
     Colombeau
    1.60
    hydrocèle
    1.59
    <unused1241>
    1.58
    <unused920>
    1.57
    <unused127>
    1.56
    Activations Density 0.001%

    No Known Activations