© 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. 78593
    Prev
    Next
    INDEX
    Explanations

    digitizing collections and papers

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

    digitize and related concepts

    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
    को
    0.50
    ः
    0.48
    ]
    0.47
     conductivity
    0.47
    د
    0.47
    ،
    0.47
    ys
    0.46
    ח
    0.46
    ले
    0.46
    POSITIVE LOGITS
    ខ្ញ
    0.48
     settim
    0.46
     восем
    0.46
    綪
    0.46
     完全
    0.45
     opravdu
    0.45
     konk
    0.44
     আমাকে
    0.44
     സാഹ
    0.44
     맞아
    0.44
    Activations Density 0.003%

    No Known Activations