© 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. 12-GEMMASCOPE-2-RES-16K
    7. 7117
    Prev
    Next
    INDEX
    Explanations

    everything from

    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
    َی
    1.68
     hasn
    1.60
     proceeds
    1.55
    之处
    1.55
    Nv
    1.50
     этих
    1.50
    ipps
    1.48
     těchto
    1.48
    你有
    1.46
    okas
    1.46
    POSITIVE LOGITS
    sia
    1.74
     sira
    1.60
    hrlich
    1.54
     construed
    1.50
    般
    1.49
     alkaline
    1.49
     หน่อย
    1.47
    ˋ
    1.47
    brow
    1.46
    dogan
    1.46
    Activations Density 0.055%

    No Known Activations