© 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. 128868
    Prev
    Next
    INDEX
    Explanations

    timeframes, accounts, and requirements

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

    Python code, music, art, 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
     棚
    0.47
    ᚗ
    0.45
    एक्स
    0.45
    WWE
    0.44
     منجر
    0.44
     месяцев
    0.44
    Avec
    0.43
     등이
    0.43
     вследствие
    0.43
     作業
    0.43
    POSITIVE LOGITS
     portrait
    0.48
    getRequest
    0.47
     midi
    0.45
     soprano
    0.45
     Rembrandt
    0.44
    !
    0.43
     recrut
    0.43
     fileobj
    0.43
    firstChild
    0.42
     chestnut
    0.42
    Activations Density 0.000%

    No Known Activations