© 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. 38660
    Prev
    Next
    INDEX
    Explanations

    verbs after to or be

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

    unwavering confidence

    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
    νει
    0.63
    噢
    0.50
    نز
    0.48
    冠軍
    0.46
    nial
    0.46
    ಧಾರ
    0.45
    nios
    0.45
     roundup
    0.44
    ubicin
    0.44
    нце
    0.44
    POSITIVE LOGITS
    ë
    0.54
    ě
    0.47
    ški
    0.46
    ellingen
    0.46
    expression
    0.46
     வெளி
    0.46
     மொழி
    0.45
    ời
    0.45
    ään
    0.45
    elijkheid
    0.44
    Activations Density 0.000%

    No Known Activations