© 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. 25158
    Prev
    Next
    INDEX
    Explanations

    linking words and punctuation

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

    punctuation and conjunctions

    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
     voilà
    0.48
    ​.
    0.46
    这也是
    0.44
     Ahí
    0.44
    。
    0.44
    ،
    0.44
    !।
    0.43
    ，
    0.43
    ፣
    0.43
    ,​
    0.42
    POSITIVE LOGITS
     religiosos
    0.45
     of
    0.45
    時に
    0.43
     diantaranya
    0.41
    সরকারী
    0.41
    際に
    0.40
     naturali
    0.39
     essendo
    0.39
    ของการ
    0.39
    लिए
    0.38
    Activations Density 0.095%

    No Known Activations