© 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. 13958
    Prev
    Next
    INDEX
    Explanations

    citations and non-English characters

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

    multilingual contexts and specific terms

    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
     muff
    0.46
     i
    0.44
    ate
    0.41
     FDA
    0.39
     crossover
    0.38
    ۍ
    0.38
     prosec
    0.38
     mallet
    0.38
    ᾳ
    0.38
     mk
    0.38
    POSITIVE LOGITS
    歡迎
    0.53
    კ
    0.52
    أ
    0.50
    ెక్టర్
    0.49
    سي
    0.48
     जाति
    0.48
    ଉ
    0.48
    這是
    0.48
    тата
    0.48
    ș
    0.48
    Activations Density 0.000%

    No Known Activations