© 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. 81004
    Prev
    Next
    INDEX
    Explanations

    Buying

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

    specific entities

    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
     компьютера
    0.50
    ประจำ
    0.49
     تصویر
    0.46
     کتاب
    0.46
     제거
    0.45
     giành
    0.45
     അടി
    0.44
    频
    0.44
     แค
    0.44
    ።
    0.44
    POSITIVE LOGITS
    尼亚克
    0.50
     eligibility
    0.47
    Buying
    0.45
    reliance
    0.44
     buying
    0.43
    বিএন
    0.42
    ન્ટે
    0.42
    Մ
    0.41
     achats
    0.41
    buying
    0.41
    Activations Density 0.007%

    No Known Activations