© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 491
    Prev
    Next
    INDEX
    Explanations

    cloud resource names

    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
    膻
    0.46
     leech
    0.40
     groupBox
    0.39
     knife
    0.39
    菜
    0.38
     ganglion
    0.38
     filet
    0.38
     shear
    0.38
     getter
    0.37
     mites
    0.37
    POSITIVE LOGITS
    }-${
    0.47
    dev
    0.46
    Unique
    0.44
    idev
    0.44
    app
    0.43
    prod
    0.43
    unique
    0.43
    your
    0.42
    deployment
    0.42
    PREFIX
    0.41
    Activations Density 0.009%

    No Known Activations