© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10225
    Prev
    Next
    INDEX
    Explanations

    <code> and quote tags

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

    technical commands and multilingual words

    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
     david
    0.43
    ’
    0.41
    waard
    0.40
    {
    0.40
     Yachts
    0.40
    ```
    0.39
    ////////////////
    0.39
    Cru
    0.39
    --------------
    0.39
    goog
    0.39
    POSITIVE LOGITS
     být
    0.43
     বিঘ
    0.42
     isolé
    0.42
     Direito
    0.42
     ভরা
    0.40
    atief
    0.40
    يب
    0.40
     recommandé
    0.40
    يم
    0.39
     мати
    0.39
    Activations Density 0.004%

    No Known Activations