© 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. 15-GEMMASCOPE-2-RES-16K
    7. 2846
    Prev
    Next
    INDEX
    Explanations

    position and distance

    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
     Wikipedia
    1.15
    import
    1.09
    igata
    1.07
    mama
    1.06
     toug
    1.04
     mož
    1.04
    工夫
    1.03
    뜻
    1.01
    』（
    1.00
     argc
    0.99
    POSITIVE LOGITS
     interstitials
    1.63
     WITHIN
    1.59
    อม
    1.57
     squarely
    1.56
     ضمن
    1.56
    ป์
    1.54
    APAC
    1.52
    ใกล้
    1.52
     mérid
    1.50
     tween
    1.49
    Activations Density 0.191%

    No Known Activations