© 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. 66669
    Prev
    Next
    INDEX
    Explanations

    cover letter

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

    cover letter

    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
    ao
    0.47
     Ao
    0.46
     {(
    0.46
     ao
    0.45
     Gaussian
    0.45
    q
    0.44
     SQL
    0.43
     trunc
    0.43
    ]{
    0.43
    DP
    0.41
    POSITIVE LOGITS
     mercados
    0.56
     stewardship
    0.52
     sociali
    0.52
     consumers
    0.51
     consumidores
    0.50
    environmental
    0.49
    🌡
    0.49
     dólares
    0.49
     पर्यावरणीय
    0.48
     mortgages
    0.48
    Activations Density 0.004%

    No Known Activations