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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 4105
    Prev
    Next
    INDEX
    Explanations

    object detection, recognition, or storage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
    AddField
    1.17
    纫
    1.14
    asati
    1.09
    s
    1.07
    맴
    1.06
     allt
    1.02
    citenamefont
    1.01
    ALTERNATIVNAMEN
    1.00
    왁
    1.00
    elolaan
    1.00
    POSITIVE LOGITS
     خواہ
    1.40
    fully
    1.38
    hadas
    1.37
    jeg
    1.36
    ized
    1.35
    chy
    1.34
    tego
    1.34
    ᵗ
    1.33
    seid
    1.33
    iesz
    1.30
    Activations Density 0.171%

    No Known Activations