© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 11729
    Prev
    Next
    INDEX
    Explanations

    listing choices

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

    formal documentation and lists

    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
     και
    0.57
     மற்றும்
    0.57
     and
    0.56
     और
    0.53
     आणि
    0.53
     এবং
    0.52
     и
    0.51
     ਅਤੇ
    0.50
     và
    0.50
     و
    0.48
    POSITIVE LOGITS
    నాన్ని
    0.34
    ettha
    0.28
    โร
    0.27
    괵
    0.27
     goTo
    0.27
     Notiflix
    0.27
    叁章
    0.27
    ัท
    0.26
    IsResolver
    0.26
    ौनक
    0.26
    Activations Density 0.075%

    No Known Activations