© 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. 120474
    Prev
    Next
    INDEX
    Explanations

    buying, selling, and journals

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

    is an

    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
     상태
    0.51
     길이
    0.45
    문
    0.44
     strangely
    0.44
     fonctionnement
    0.43
     atteggi
    0.43
     merav
    0.42
     suitability
    0.41
     aston
    0.41
     독립
    0.41
    POSITIVE LOGITS
     Thur
    0.52
     C
    0.48
     Sah
    0.46
     Dolls
    0.45
     Ele
    0.45
     chauff
    0.45
    yla
    0.44
     sah
    0.44
     黃
    0.44
     Painters
    0.44
    Activations Density 0.000%

    No Known Activations