© 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. 196
    Prev
    Next
    INDEX
    Explanations

    years dates

    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
     ✅
    0.77
    рина
    0.63
    hada
    0.55
    umet
    0.52
    chod
    0.49
    onom
    0.49
     mắt
    0.48
    irá
    0.47
     ⭐
    0.47
     gör
    0.47
    POSITIVE LOGITS
    9
    2.07
    7
    2.03
    8
    2.02
    6
    2.02
    5
    1.92
    4
    1.87
    0
    1.87
    3
    1.86
    2
    1.81
     flushed
    1.70
    Activations Density 0.497%

    No Known Activations