© 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. 248244
    Prev
    Next
    INDEX
    Explanations

    quantities of time

    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
    е
    0.55
    SEO
    0.51
    la
    0.51
    Bitcoin
    0.50
    cigarettes
    0.50
    IEEE
    0.48
    5
    0.48
    red
    0.47
    furt
    0.47
    financial
    0.47
    POSITIVE LOGITS
     závod
    0.48
     サイズ
    0.48
     CREATE
    0.47
     Sizes
    0.46
     নীর
    0.45
    攢
    0.45
     นับ
    0.45
     måtte
    0.44
    <unused411>
    0.44
     toler
    0.44
    Activations Density 0.001%

    No Known Activations