© 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. 53138
    Prev
    Next
    INDEX
    Explanations

    social context studies

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

    after conjunctions or punctuation

    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
     Необходимо
    0.30
     Франция
    0.30
     I
    0.29
     દેશ
    0.29
    sim
    0.28
    tal
    0.28
    yyyy
    0.28
    yaan
    0.28
    .'
    0.28
     बीते
    0.28
    POSITIVE LOGITS
     molécules
    0.28
    ွဲ
    0.27
    োঁয়া
    0.27
    드는
    0.26
    শক্ত
    0.26
    秏
    0.26
    লি
    0.26
    唬
    0.26
     ensembles
    0.25
     aplatis
    0.25
    Activations Density 0.000%

    No Known Activations