© 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. 14343
    Prev
    Next
    INDEX
    Explanations

    career and time periods

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

    his pronouns in multiple languages

    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
     yourselves
    0.55
    每一個
    0.50
     sinusoidal
    0.49
    CHECK
    0.49
    我们需要
    0.49
    ㄩ
    0.49
     configuration
    0.48
     የሚ
    0.48
     nếu
    0.48
     각
    0.48
    POSITIVE LOGITS
     vuonna
    0.75
     Jahre
    0.74
     později
    0.73
     jego
    0.71
     njegov
    0.70
     carrière
    0.68
     njegove
    0.68
     Karriere
    0.67
     menikah
    0.67
     jeho
    0.66
    Activations Density 0.077%

    No Known Activations