© 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. 177940
    Prev
    Next
    INDEX
    Explanations

    foreign and specific technical terms

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

    then, ultimately, comes

    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
    -
    0.45
    يكون
    0.45
    Добрый
    0.43
    é
    0.43
    Answer
    0.43
    vais
    0.42
     (
    0.42
    раи
    0.42
    du
    0.41
    por
    0.41
    POSITIVE LOGITS
     انھیں
    0.52
     phenols
    0.49
    ardı
    0.48
    㙂
    0.48
    äden
    0.47
    నాలు
    0.47
     qīng
    0.46
     તાલુ
    0.46
    ppings
    0.46
    sthresh
    0.46
    Activations Density 0.001%

    No Known Activations