© 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. 11945
    Prev
    Next
    INDEX
    Explanations

    sponsorship and funding

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

    sponsorship and funding

    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
    🗸
    0.46
     ఎలా
    0.43
     arqué
    0.43
     jossa
    0.43
    
    0.42
     rougeâtre
    0.42
     eliminación
    0.42
    bigsqcup
    0.42
    🤔
    0.41
     compressibility
    0.41
    POSITIVE LOGITS
     Sponsors
    0.99
     sponsors
    0.93
     sponsorship
    0.92
     sponsored
    0.87
     Sponsor
    0.87
     sponsor
    0.86
     sponsorships
    0.80
     spons
    0.78
     sponsoring
    0.78
     patrocin
    0.76
    Activations Density 0.063%

    No Known Activations