© 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. 53746
    Prev
    Next
    INDEX
    Explanations

    numbers and counts

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

    mathematical calculations and additions

    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
    دا
    0.44
     loạt
    0.43
     Yemek
    0.43
    Rex
    0.41
     Rex
    0.41
     بدأ
    0.40
    ③
    0.40
     اص
    0.39
     kezd
    0.39
     سید
    0.39
    POSITIVE LOGITS
     chromosomal
    0.46
     wm
    0.46
     gigantic
    0.41
     empires
    0.38
     wars
    0.38
     empire
    0.38
     wv
    0.38
     nineteen
    0.38
     পাকিস্তানে
    0.37
     ono
    0.37
    Activations Density 0.014%

    No Known Activations