© 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. 41152
    Prev
    Next
    INDEX
    Explanations

    Our IL dentists

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

    introduction of lists of factors or features

    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
    及び
    0.45
    ช่วย
    0.42
     gleichen
    0.41
    및
    0.40
    および
    0.39
    及
    0.38
     ช่วย
    0.37
     及び
    0.37
     및
    0.37
     thereby
    0.36
    POSITIVE LOGITS
    㼛
    0.47
    বিত্র
    0.42
     लहंगा
    0.40
    occhi
    0.40
    abilité
    0.38
    虻
    0.38
    昛
    0.37
     affordability
    0.37
    गमेंट
    0.37
    安全性
    0.37
    Activations Density 0.022%

    No Known Activations