© 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. 157283
    Prev
    Next
    INDEX
    Explanations

    universal console

    np_acts-logits-general · gemini-2.5-flash-lite

    math and code syntax

    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
    immersive
    0.49
     درمیان
    0.48
    y
    0.47
     ذریع
    0.46
     Nvidia
    0.46
    ">→</
    0.45
     تبدی
    0.45
     аллер
    0.45
     nitrog
    0.45
    ing
    0.44
    POSITIVE LOGITS
    Бар
    0.47
    Ὑ
    0.47
    zier
    0.46
    Ὁ
    0.46
    !’
    0.43
    jegyz
    0.42
     সদা
    0.42
    ECK
    0.41
    Detach
    0.41
    Free
    0.41
    Activations Density 0.000%

    No Known Activations