© 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. 45854
    Prev
    Next
    INDEX
    Explanations

    services available

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

    descriptions, requirements, and connections

    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
    
    0.53
    报
    0.50
    orse
    0.49
     \%
    0.48
    oris
    0.47
    rpt
    0.47
    oe
    0.46
    mselves
    0.46
     முன்ன
    0.44
    \%
    0.44
    POSITIVE LOGITS
     În
    0.53
     It
    0.51
    În
    0.50
    κού
    0.50
     Avenger
    0.47
    フィット
    0.47
     Ararat
    0.46
     Destroyer
    0.46
     Salvatore
    0.46
     At
    0.45
    Activations Density 0.000%

    No Known Activations