© 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. 209999
    Prev
    Next
    INDEX
    Explanations

    fabrication at

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

    native language and technical terms

    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
     substantially
    0.48
     precipitation
    0.48
     Precipitation
    0.47
     precipitate
    0.47
     safari
    0.44
     让
    0.43
     通过
    0.43
    机会
    0.43
     Recreation
    0.42
     Safari
    0.42
    POSITIVE LOGITS
    パリ
    0.52
     विरोधी
    0.50
    мини
    0.49
    wrote
    0.49
    हम
    0.49
    хо
    0.47
    sorry
    0.47
    kati
    0.46
     בל
    0.46
     odbior
    0.46
    Activations Density 0.001%

    No Known Activations