© 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. 186222
    Prev
    Next
    INDEX
    Explanations

    time, potential, lawyers, owners, collapse

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

    common grammatical structures

    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
    byteArray
    0.50
     semicol
    0.48
    7
    0.48
    6
    0.47
     וא
    0.47
    να
    0.46
     стра
    0.46
    vals
    0.46
    5
    0.46
     luces
    0.46
    POSITIVE LOGITS
     Jason
    0.46
     Maui
    0.45
     Team
    0.43
    洄
    0.42
    DebugTest
    0.42
     inbound
    0.42
    Maui
    0.42
    हिमा
    0.42
     måle
    0.42
     GitLab
    0.42
    Activations Density 0.001%

    No Known Activations