© 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. 35282
    Prev
    Next
    INDEX
    Explanations

    jerk, burpees, ergothioneine, Narcissistic

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

    words in definitions or lists

    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
    ت
    1.19
    ع
    1.18
     for
    0.96
    EL
    0.94
    م
    0.94
    一些
    0.92
    AL
    0.88
    י
    0.85
    ك
    0.84
    小米
    0.82
    POSITIVE LOGITS
    ிய
    0.81
    ться
    0.80
    ших
    0.80
    ков
    0.73
    padă
    0.71
    шинство
    0.70
    чи
    0.69
    ći
    0.68
    نی
    0.67
    ani
    0.66
    Activations Density 0.406%

    No Known Activations