© 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. 311
    Prev
    Next
    INDEX
    Explanations

    longer, larger, or extended topics

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

    larger numbers and more

    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
     равна
    0.44
     Fraction
    0.43
    萦
    0.42
     ентитету
    0.42
     بسرعة
    0.42
     constituting
    0.41
    cepat
    0.40
    ্জন
    0.40
     掛
    0.40
     speeding
    0.40
    POSITIVE LOGITS
     longer
    0.56
     بیشتری
    0.53
    もっと
    0.49
    longer
    0.49
    更大的
    0.48
    継続
    0.48
     longterm
    0.48
     längre
    0.47
     훨씬
    0.47
     more
    0.46
    Activations Density 0.000%

    No Known Activations