© 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. 13460
    Prev
    Next
    INDEX
    Explanations

    and poor, and TLC

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

    weights, portfolio, rgb, hash, Bethesda

    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
    ل
    0.50
    ال
    0.48
     pique
    0.47
    小
    0.45
    &
    0.44
    aquest
    0.43
    ام
    0.42
    "
    0.42
    Imaging
    0.42
     sò
    0.42
    POSITIVE LOGITS
     પૂર્ણ
    0.54
     ደረጃ
    0.52
     ел
    0.50
     場
    0.48
    ribu
    0.47
     плюс
    0.47
     等
    0.46
    ऊदी
    0.46
     тощо
    0.46
    場で
    0.45
    Activations Density 0.000%

    No Known Activations