© 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. 201650
    Prev
    Next
    INDEX
    Explanations

    common phrases and conjunctions

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

    origins, independent, applicable

    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
     Chartered
    0.42
     microbial
    0.41
     phẳng
    0.41
     effluent
    0.41
     Networks
    0.40
     industry
    0.39
     estimator
    0.39
    ὸ
    0.39
    ریت
    0.39
     perio
    0.38
    POSITIVE LOGITS
    yes
    0.50
    ígenes
    0.49
    日本人
    0.49
     മറ്റ
    0.48
    ploidy
    0.47
    千葉
    0.47
    is
    0.46
    woocommerce
    0.46
    ემა
    0.46
    ច្រើន
    0.46
    Activations Density 0.000%

    No Known Activations