© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 5732
    Prev
    Next
    INDEX
    Explanations

    in short, to lose

    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_12_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
     integrantes
    1.36
     composers
    1.35
     depleted
    1.35
     Mehndi
    1.32
    jük
    1.29
     gunmen
    1.28
     neurons
    1.28
    ୍
    1.28
    ରା
    1.28
     opioid
    1.27
    POSITIVE LOGITS
    pras
    1.64
    wasser
    1.61
    予
    1.60
    acam
    1.60
    primer
    1.60
    сю
    1.56
    figer
    1.56
    essi
    1.55
    rotto
    1.54
    образ
    1.54
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.