© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 48097
    Prev
    Next
    INDEX
    Explanations

    craft beer/wine/whiskey set

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :
    0.44
    重要
    0.44
     jed
    0.39
     allergy
    0.39
     amministrat
    0.38
     popularity
    0.38
    .
    0.38
     autism
    0.37
     Illinois
    0.37
     outsourced
    0.37
    POSITIVE LOGITS
    ୯
    0.48
    ？）
    0.47
    ១
    0.46
    closePath
    0.46
     également
    0.45
    剻
    0.45
    놁
    0.45
    ຜະລິດຕ
    0.44
    жеб
    0.44
    ाब
    0.44
    Activations Density 0.001%

    No Known Activations