© 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. 79690
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases

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

    abstracts and non-English characters

    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
     革
    0.53
    utérus
    0.52
     Unidos
    0.51
     Utah
    0.50
     inflamed
    0.50
     республи
    0.49
     Crohn
    0.48
     :',
    0.48
     উত্তরা
    0.48
     oy
    0.48
    POSITIVE LOGITS
    יה
    0.59
    ע
    0.54
    不少
    0.53
    В
    0.48
    많은
    0.47
    ві
    0.46
    يش
    0.46
    К
    0.46
    πε
    0.44
    Nowadays
    0.44
    Activations Density 0.000%

    No Known Activations