© 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. 233861
    Prev
    Next
    INDEX
    Explanations

    engineering specializing

    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
     የአ
    0.49
     Athenians
    0.46
    я
    0.46
    ág
    0.45
    ι
    0.45
    તાવ
    0.45
    الة
    0.43
     разу
    0.43
    áce
    0.43
    ancies
    0.43
    POSITIVE LOGITS
     neh
    0.46
    ミラ
    0.45
    レシピ
    0.44
     mh
    0.44
    .
    0.43
    られます
    0.43
     monochromatic
    0.42
     pixel
    0.42
    IBRARY
    0.42
     nonostante
    0.41
    Activations Density 0.000%

    No Known Activations