© 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. 51705
    Prev
    Next
    INDEX
    Explanations

    dates and days of week

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

    resource, treatments, language

    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
     खरीदना
    0.52
    UEFA
    0.47
    Número
    0.47
     ባህ
    0.45
    ブーツ
    0.45
    بازی
    0.45
    }}}-\
    0.44
    Política
    0.44
    決勝
    0.44
    ށ
    0.43
    POSITIVE LOGITS
     wolf
    0.54
     vom
    0.53
     gl
    0.52
    ars
    0.50
     ure
    0.49
     invaded
    0.49
     hex
    0.49
     smelt
    0.48
    ations
    0.48
     g
    0.47
    Activations Density 0.001%

    No Known Activations