© 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. 69819
    Prev
    Next
    INDEX
    Explanations

    street photography

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

    non-english scripts

    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
     n
    0.50
     with
    0.50
     biology
    0.46
     dir
    0.46
     ,
    0.46
     rohkem
    0.45
     mukaan
    0.44
     बाली
    0.44
     biologist
    0.44
     dire
    0.43
    POSITIVE LOGITS
    ისა
    0.54
    ítě
    0.48
    麃
    0.46
    ρί
    0.46
    ಗೊಳ
    0.46
    ắn
    0.45
     ಪಾ
    0.44
    などが
    0.44
    ність
    0.44
     கெல்வின்
    0.43
    Activations Density 0.001%

    No Known Activations