© 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. 245052
    Prev
    Next
    INDEX
    Explanations

    adverbial endings and specific terms

    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
     TODOS
    0.53
     üks
    0.50
     puncak
    0.50
    ಬಹು
    0.50
    ק
    0.50
     yks
    0.49
    ס
    0.48
     FOUND
    0.48
    س
    0.48
    VAE
    0.47
    POSITIVE LOGITS
    ly
    0.52
     المختلف
    0.50
    ově
    0.46
     Chev
    0.45
    tiktok
    0.45
    useState
    0.44
     পার্টি
    0.44
     পাঠকের
    0.43
    oader
    0.43
    setDescription
    0.43
    Activations Density 0.000%

    No Known Activations