© 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. 29840
    Prev
    Next
    INDEX
    Explanations

    data; rankings; full; old; password; split

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

    code/programming context

    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
    ḧ
    0.61
    Deprecated
    0.57
    Ṛ
    0.57
     फ़रवरी
    0.55
    Tabuleiro
    0.54
    﨑
    0.54
    ḍ
    0.51
    _{\{
    0.50
     பாண்டிய
    0.50
    Nieder
    0.50
    POSITIVE LOGITS
    0.56
     dinner
    0.49
     microwaves
    0.47
     glassware
    0.47
     hormone
    0.46
     athletic
    0.46
     food
    0.46
     manure
    0.46
     planters
    0.46
     staffing
    0.46
    Activations Density 0.000%

    No Known Activations