© 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. 202229
    Prev
    Next
    INDEX
    Explanations

    specific word pairings

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

    interdisciplinary 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
     Росії
    0.54
    प्लाई
    0.52
    অপহরণ
    0.50
     sogenannte
    0.49
     sogenannten
    0.49
    istische
    0.48
     pajamas
    0.48
    뎐
    0.48
    stufe
    0.48
     Україні
    0.47
    POSITIVE LOGITS
     Housing
    0.46
     Difficulty
    0.45
     Bank
    0.44
     \
    0.44
     District
    0.44
     Workshop
    0.43
    >.
    0.43
    0
    0.43
    K
    0.43
     Practitioner
    0.42
    Activations Density 0.000%

    No Known Activations