© 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. 83698
    Prev
    Next
    INDEX
    Explanations

    people, customers, lovers

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

    the phrase follows list items

    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
     도
    0.49
    시기
    0.47
     அதன்
    0.44
    Sec
    0.43
    Р
    0.43
    悭
    0.43
     яе
    0.43
     용
    0.43
    材質
    0.42
    접
    0.42
    POSITIVE LOGITS
     cárc
    0.54
     blasting
    0.51
     combos
    0.50
     blasts
    0.49
    没人
    0.47
     clowns
    0.46
     Disabilities
    0.45
     desserts
    0.45
     plastered
    0.45
     কারাগারে
    0.45
    Activations Density 0.002%

    No Known Activations