© 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. 223653
    Prev
    Next
    INDEX
    Explanations

    historical data analysis

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

    OpenAI's possessive

    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
     第一
    0.52
     ríos
    0.50
     incluyendo
    0.49
     NOAA
    0.49
     समुद्री
    0.49
     這
    0.49
     загряз
    0.49
     Bismillahirrah
    0.48
     ನನಗೆ
    0.48
     केले
    0.48
    POSITIVE LOGITS
    ,
    0.51
     asked
    0.48
    acing
    0.46
     squad
    0.46
     bowed
    0.45
    ITICAL
    0.44
    ängt
    0.44
    st
    0.43
     ,
    0.43
     cation
    0.42
    Activations Density 0.001%

    No Known Activations