© 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. 139510
    Prev
    Next
    INDEX
    Explanations

    last names

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

    proper nouns and street names

    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
     интенсив
    0.54
     прод
    0.53
     العالم
    0.53
     الاثنين
    0.51
     اليوم
    0.49
     ყ
    0.49
     енер
    0.49
     Ж
    0.48
     أمس
    0.47
    軺
    0.47
    POSITIVE LOGITS
     Smith
    0.63
     Jackson
    0.58
     Stewart
    0.51
     Gutierrez
    0.50
     Hed
    0.50
     smith
    0.50
     Maple
    0.49
     Mant
    0.49
     Brown
    0.49
     Becker
    0.48
    Activations Density 0.000%

    No Known Activations