© 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. 4357
    Prev
    Next
    INDEX
    Explanations

    options a letter followed by a period or parenthesis

    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
    a
    4.23
    e
    4.13
    的
    4.08
    ه
    3.94
    s
    3.87
    י
    3.76
    ي
    3.75
    y
    3.71
    i
    3.66
    er
    3.50
    POSITIVE LOGITS
    ülő
    2.36
    ariye
    2.21
    ounc
    2.07
    ientras
    2.06
    aturally
    2.04
    ække
    1.99
     medulla
    1.98
    ıldı
    1.98
    icylic
    1.97
    isection
    1.97
    Activations Density 0.039%

    No Known Activations