© 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. 172684
    Prev
    Next
    INDEX
    Explanations

    automatic configuration

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

    expansion followed by continued

    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
    Bill
    0.51
    T
    0.47
    Mack
    0.46
     tradicionales
    0.46
    诋
    0.45
    Buck
    0.45
    Simon
    0.45
    Brent
    0.44
    詆
    0.44
    Daddy
    0.43
    POSITIVE LOGITS
     metamorphosis
    0.45
     bgcolor
    0.45
     Paths
    0.44
     мира
    0.42
     transmutation
    0.42
     βά
    0.42
     Researcher
    0.42
     ~,
    0.42
     軍
    0.42
     余
    0.41
    Activations Density 0.000%

    No Known Activations