© 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. 53-GEMMASCOPE-2-RES-65K
    7. 6927
    Prev
    Next
    INDEX
    Explanations

    Xpecial

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

    Gemma team safety guidelines

    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_53_width_65k_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
     J
    0.61
    J
    0.54
    𝒋
    0.49
    𝐽
    0.45
     Sass
    0.43
     JAS
    0.42
     ज
    0.41
     UART
    0.41
     ஜ
    0.40
     Three
    0.39
    POSITIVE LOGITS
    Jeff
    0.75
     Jeff
    0.70
    jeff
    0.64
     jeff
    0.60
     Jeffery
    0.55
     Jeffrey
    0.44
    Jeffrey
    0.44
    Benefit
    0.40
    地
    0.39
    Debut
    0.39
    Activations Density 0.020%

    No Known Activations