© 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. 197354
    Prev
    Next
    INDEX
    Explanations

    specific items or types

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

    introduces subsequent actions or entities

    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
    s
    0.54
    y
    0.52
    d
    0.47
    ا
    0.46
    at
    0.45
    tkinter
    0.45
    o
    0.44
    ép
    0.44
    ning
    0.44
    routes
    0.44
    POSITIVE LOGITS
     vadati
    0.52
     já
    0.49
     സ്ത്ര
    0.49
     yaad
    0.49
     這個
    0.48
     Page
    0.48
     palav
    0.48
     recentemente
    0.48
     rapat
    0.47
    ത്തിനും
    0.46
    Activations Density 0.000%

    No Known Activations