© 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. 77041
    Prev
    Next
    INDEX
    Explanations

    bearing Explorer

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

    operations models Transformer

    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
     ironically
    0.48
     aliments
    0.47
    ר
    0.46
     leftist
    0.46
    買取
    0.46
     소비
    0.45
     politicians
    0.45
     charities
    0.45
     bombarded
    0.45
     perif
    0.45
    POSITIVE LOGITS
     Tasks
    0.46
     Directors
    0.43
    षा
    0.43
    任务
    0.40
     Klo
    0.39
    หว่าง
    0.39
     Canoe
    0.39
     });
    0.38
     Serial
    0.38
     Packages
    0.38
    Activations Density 0.005%

    No Known Activations