© 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. 135242
    Prev
    Next
    INDEX
    Explanations

    hereinafter referred to as

    np_acts-logits-general · gemini-2.5-flash-lite

    what something offers

    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
    #,
    0.46
     hallways
    0.44
     protectors
    0.43
    LIST
    0.43
     commences
    0.43
    আন্তর্জাতিক
    0.42
    \#
    0.42
    カード
    0.41
     collisions
    0.41
     আর্জেন্টিনা
    0.41
    POSITIVE LOGITS
     แม
    0.47
     Intense
    0.47
     Nasa
    0.47
     Loch
    0.46
     Being
    0.46
    夥
    0.45
     Innocent
    0.45
    omie
    0.44
     Loom
    0.44
     परफॉर्म
    0.44
    Activations Density 0.001%

    No Known Activations