© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 6002
    Prev
    Next
    INDEX
    Explanations

    name __, status _

    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
     варі
    1.73
    واع
    1.67
    盤
    1.64
    umia
    1.59
     Briefly
    1.52
     audiencia
    1.50
    Sphere
    1.49
     OPTIONS
    1.48
     Documents
    1.47
    righteous
    1.47
    POSITIVE LOGITS
    芍
    1.50
     gills
    1.49
     peony
    1.49
    häng
    1.47
     jacuzzi
    1.44
    游泳
    1.41
     botanique
    1.41
    anganese
    1.40
    жала
    1.36
     Cortes
    1.35
    Activations Density 0.005%

    No Known Activations