© 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. 170199
    Prev
    Next
    INDEX
    Explanations

    foursquare fellow

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

    using `/` or quotes

    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
     লোভ
    0.46
    𝐜
    0.45
    ופי
    0.45
     NOTES
    0.43
    ໋
    0.43
    盜
    0.43
    losti
    0.43
    ল
    0.43
    বাজারে
    0.42
    蓋
    0.42
    POSITIVE LOGITS
     رع
    0.45
    诠
    0.44
     внеш
    0.44
    ikin
    0.42
    ett
    0.39
    idents
    0.39
    reate
    0.39
     تاکید
    0.39
     ट्रांसपोर्ट
    0.39
    人才
    0.39
    Activations Density 0.001%

    No Known Activations