© 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. 6018
    Prev
    Next
    INDEX
    Explanations

    specific types or categories

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

    scenario, Python, tendency, concern, holding, UT, confident, urges

    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
     policías
    0.61
    সে
    0.55
     seguimiento
    0.53
    م
    0.52
     recebe
    0.52
    ю
    0.52
     crescimento
    0.51
     comerciales
    0.50
     recibe
    0.49
     receber
    0.49
    POSITIVE LOGITS
     घंटों
    0.49
     Classics
    0.48
    Word
    0.47
    tze
    0.46
     ngũ
    0.46
    oulton
    0.45
    .$$
    0.44
     woord
    0.44
    ДО
    0.43
     interdiscipl
    0.42
    Activations Density 0.000%

    No Known Activations