© 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. 246333
    Prev
    Next
    INDEX
    Explanations

    products from additives

    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
     alternatives
    0.47
    JACK
    0.46
    괵
    0.46
     ways
    0.44
    ransfer
    0.44
    Quan
    0.44
     methods
    0.42
    swald
    0.41
    vous
    0.41
    nington
    0.41
    POSITIVE LOGITS
     сельскохозяй
    0.48
    iune
    0.48
     روپے
    0.47
    い
    0.47
    ٹنے
    0.46
     Elovl
    0.46
    TouchUpInside
    0.46
    を購入
    0.44
    pointee
    0.44
     palvel
    0.44
    Activations Density 0.001%

    No Known Activations