© 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. 18487
    Prev
    Next
    INDEX
    Explanations

    numbers in parentheses

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

    collagen production and DNA repair

    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
    远的
    0.39
    <sub>
    0.39
     ছাত্রলীগ
    0.38
     Facultad
    0.37
    远
    0.37
    Sitting
    0.36
    ()/
    0.36
    Essa
    0.36
    要么
    0.36
    远远
    0.35
    POSITIVE LOGITS
     प्रूफ
    0.44
     nem
    0.42
    proof
    0.42
     वसु
    0.41
    度假
    0.41
     mø
    0.39
    斫
    0.39
     Nxc
    0.39
     custod
    0.39
     Nyl
    0.39
    Activations Density 0.000%

    No Known Activations