© 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. 138662
    Prev
    Next
    INDEX
    Explanations

    descriptive words with purpose

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

    creating and essential

    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
     լ
    0.57
     وی
    0.54
     لوی
    0.52
     благодаря
    0.50
     svou
    0.49
     половине
    0.48
     بع
    0.48
     свою
    0.48
     پیسو
    0.48
     இடத்தை
    0.47
    POSITIVE LOGITS
     mik
    0.51
     unfair
    0.50
     mikro
    0.48
    тел
    0.43
     katalog
    0.43
     obtain
    0.42
    त
    0.42
    Seven
    0.41
    etzen
    0.41
    teki
    0.41
    Activations Density 0.000%

    No Known Activations