© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9131
    Prev
    Next
    INDEX
    Explanations

    common words after punctuation

    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_40_width_16k_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
     Additionally
    0.41
    也没
    0.41
    也沒有
    0.40
     করেও
    0.40
    也不能
    0.39
     Nich
    0.38
    倒是
    0.38
    $"
    0.36
     Fos
    0.36
     Schaff
    0.35
    POSITIVE LOGITS
     الَّذ
    0.52
     bahwa
    0.52
     sebuah
    0.52
     bahawa
    0.48
     yaitu
    0.46
    នូវ
    0.45
    ância
    0.42
    beautiful
    0.42
     அதாவது
    0.41
    namely
    0.41
    Activations Density 0.344%

    No Known Activations