© 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. 165568
    Prev
    Next
    INDEX
    Explanations

    numbers and multilingual words

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

    numbers and occurrences

    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
     increases
    0.47
    相机
    0.46
    .
    0.45
    Homes
    0.44
    芸
    0.42
     separation
    0.42
    锡
    0.42
     C
    0.41
     get
    0.41
    ел
    0.41
    POSITIVE LOGITS
     শ্রদ্ধ
    0.54
     चालीस
    0.54
    thirty
    0.47
     പ്രത്യ
    0.46
    あるいは
    0.46
     अध्या
    0.45
    opathological
    0.45
    bra
    0.44
     কিংবা
    0.44
    adeso
    0.43
    Activations Density 0.001%

    No Known Activations