© 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. 260239
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     ඕ
    0.44
    Establish
    0.43
    חנו
    0.43
    スパ
    0.43
    マスク
    0.43
    キシ
    0.43
     Ilana
    0.43
    驼
    0.43
     distintas
    0.42
    buds
    0.42
    POSITIVE LOGITS
     Nummer
    0.50
     والط
    0.49
    عدد
    0.45
    লা
    0.45
     số
    0.45
     nummer
    0.45
     la
    0.44
     Tex
    0.43
     numer
    0.42
    ла
    0.41
    Activations Density 0.000%

    No Known Activations