© 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. 5540
    Prev
    Next
    INDEX
    Explanations

    L words

    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
    ldata
    1.99
    จัย
    1.91
    houettes
    1.83
    keyDown
    1.80
     NoSuch
    1.78
    ے
    1.75
    тод
    1.74
    慑
    1.70
    porcion
    1.68
     Jong
    1.67
    POSITIVE LOGITS
    novel
    2.06
    aredo
    2.01
    ার্ভ
    2.01
     sáb
    1.88
    dzić
    1.85
    ễ
    1.81
    신도시
    1.81
    ässig
    1.73
     علما
    1.68
    edges
    1.64
    Activations Density 0.041%

    No Known Activations