© 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. 227372
    Prev
    Next
    INDEX
    Explanations

    strips in arrangement

    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
    说了
    0.47
    Coach
    0.46
    Lotus
    0.46
    Represent
    0.45
    限界
    0.42
    >):
    0.41
    Campus
    0.41
     symplectic
    0.41
    Produce
    0.41
    投资
    0.40
    POSITIVE LOGITS
     グラ
    0.53
     見
    0.50
     機械
    0.50
     因為
    0.49
    ಳ್ಳ
    0.48
    lectricité
    0.47
     技術
    0.47
    LIOGRAPHY
    0.47
     Kỳ
    0.46
     rapide
    0.46
    Activations Density 0.001%

    No Known Activations