© 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. 4694
    Prev
    Next
    INDEX
    Explanations

    countries, Portugal

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

    white hat

    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
    도
    0.50
    voll
    0.49
    в
    0.49
    г
    0.47
     Mind
    0.47
    unya
    0.46
    ना
    0.46
    h
    0.46
    이며
    0.45
     Mit
    0.43
    POSITIVE LOGITS
    chaoxing
    0.57
    abhavo
    0.55
     バー
    0.55
    東北
    0.54
    ᵑ
    0.53
    ｀)
    0.52
     tumeurs
    0.52
    簍
    0.51
     serão
    0.50
    開心
    0.50
    Activations Density 0.000%

    No Known Activations