© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 30489
    Prev
    Next
    INDEX
    Explanations

    code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    这么多
    0.38
    {
    0.36
     쉽
    0.35
     دیکھا
    0.35
    EDEN
    0.34
    akat
    0.34
     emozioni
    0.33
    ESTER
    0.33
    ይን
    0.33
    Ẩ
    0.33
    POSITIVE LOGITS
     Dadurch
    0.43
    origines
    0.40
    acuse
    0.39
     Mannschaften
    0.38
     medida
    0.38
     Außerdem
    0.38
     Rothschild
    0.38
    Ainsi
    0.38
     dysplasia
    0.38
    한다는
    0.38
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.