© 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. 5303
    Prev
    Next
    INDEX
    Explanations

    categories and descriptions

    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
    S
    0.49
    x
    0.49
    측
    0.47
    Cite
    0.46
    도를
    0.45
     Hoa
    0.44
    Hoa
    0.44
    F
    0.44
    ABI
    0.43
    低的
    0.43
    POSITIVE LOGITS
    子ども
    0.55
     bambino
    0.54
    唒
    0.51
     belang
    0.49
     euh
    0.49
    𝔬
    0.48
     comentários
    0.47
    เรื่อง
    0.47
     jellem
    0.47
     malade
    0.46
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.