© 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. 36248
    Prev
    Next
    INDEX
    Explanations

    retailer names and brands

    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
     Yama
    0.46
    泛
    0.45
    ោយ
    0.45
    پے
    0.44
     Populate
    0.43
     operand
    0.42
     Beispiele
    0.42
     annotate
    0.42
    蓴
    0.42
     Derive
    0.42
    POSITIVE LOGITS
    Walmart
    0.80
     Walmart
    0.71
     walmart
    0.63
     Walgreens
    0.57
     Kroger
    0.54
    Extra
    0.50
    EXTRA
    0.50
     Kirkland
    0.49
     grilling
    0.48
     Extra
    0.47
    Activations Density 0.021%

    No Known Activations