© 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. 232889
    Prev
    Next
    INDEX
    Explanations

    puppy starter packs

    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
    ウン
    0.50
    🧈
    0.46
    permutation
    0.46
    たとえば
    0.45
     преодо
    0.45
     типи
    0.44
    например
    0.44
    担任
    0.43
     приветствую
    0.43
     言っ
    0.43
    POSITIVE LOGITS
     Courtesy
    0.51
     Galleria
    0.48
     courtesy
    0.47
     “
    0.47
     sub
    0.46
    
    0.46
     Channel
    0.46
     Error
    0.46
     Mỗi
    0.44
     Hover
    0.44
    Activations Density 0.001%

    No Known Activations