© 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. 40-GEMMASCOPE-2-RES-262K
    7. 131898
    Prev
    Next
    INDEX
    Explanations

    how to make cookie dough

    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_40_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
    搞笑
    0.43
    airy
    0.40
    暱
    0.39
    érico
    0.39
     நடித்த
    0.38
     héro
    0.38
    ikulum
    0.38
    iel
    0.37
     héros
    0.37
    හාර
    0.37
    POSITIVE LOGITS
     progn
    0.42
     lifestyle
    0.39
    綜
    0.39
    แม่
    0.38
    出于
    0.38
     সম্পর্কে
    0.37
     gros
    0.37
     subpar
    0.37
    ぶりに
    0.36
     cad
    0.36
    Activations Density 0.001%

    No Known Activations