© 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. 182624
    Prev
    Next
    INDEX
    Explanations

    box, collection, instructions, needed

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

    modal verbs and "intricate works"

    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
    եղ
    0.52
    ազ
    0.51
    Ղ
    0.48
    ীত
    0.48
    setlength
    0.48
    ণিত
    0.46
    বৃত্ত
    0.46
    ăț
    0.45
     zawier
    0.44
    віт
    0.44
    POSITIVE LOGITS
     ڈ
    0.46
     پا
    0.46
     لگتا
    0.44
    branes
    0.44
    ↵
    0.44
     ನಲ್ಲಿ
    0.44
    OPH
    0.43
     ابتدا
    0.43
     bubbly
    0.43
     کرونا
    0.42
    Activations Density 0.000%

    No Known Activations