© 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. 7-GEMMASCOPE-2-RES-16K
    7. 12735
    Prev
    Next
    INDEX
    Explanations

    date and time expressions

    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_7_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
    sensors
    1.96
     milliseconds
    1.96
     интерфей
    1.94
    tics
    1.93
    碜
    1.92
    ྥ
    1.90
     accueil
    1.89
     microns
    1.89
    вшийся
    1.85
    Controllers
    1.84
    POSITIVE LOGITS
    a
    1.59
    ingh
    1.56
    ATO
    1.54
    atts
    1.53
    estimate
    1.52
    igna
    1.51
    </em>
    1.50
    estimating
    1.49
    erto
    1.49
     pag
    1.48
    Activations Density 0.000%

    No Known Activations