© 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. 124207
    Prev
    Next
    INDEX
    Explanations

    We will

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

    reading or reports for stakeholders

    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
     保存
    0.52
    ৭
    0.48
    螈
    0.47
     документи
    0.46
     документа
    0.45
    там
    0.44
     বিদ্ব
    0.44
     বৃ
    0.44
     mesmerizing
    0.44
    тран
    0.43
    POSITIVE LOGITS
     breakdown
    0.48
     OJ
    0.48
     vanuit
    0.46
     जाता
    0.45
     core
    0.45
     airline
    0.43
     PAGE
    0.43
    鈞
    0.43
     Olympia
    0.43
     acres
    0.43
    Activations Density 0.000%

    No Known Activations