© 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. 181477
    Prev
    Next
    INDEX
    Explanations

    phrases after common words

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

    sizes, states, and impact

    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
    nych
    0.45
    वल
    0.44
    щу
    0.44
    當年
    0.43
    odio
    0.43
    ሩ
    0.42
    चय
    0.41
    ext
    0.41
    ict
    0.40
    ibid
    0.39
    POSITIVE LOGITS
     breads
    0.54
    糰
    0.51
     dumplings
    0.51
    封装
    0.50
     wafers
    0.50
     aromatic
    0.49
     temperatures
    0.49
     syrups
    0.49
     muffins
    0.48
     tablets
    0.47
    Activations Density 0.001%

    No Known Activations