© 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. 73359
    Prev
    Next
    INDEX
    Explanations

    paid benefits or services

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

    paid services or time off

    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
    ت
    0.58
    تهم
    0.54
    تش
    0.53
    فهام
    0.51
    ي
    0.49
    comodule
    0.49
    lığı
    0.48
    ０
    0.48
    
    0.48
    މ
    0.47
    POSITIVE LOGITS
    ir
    0.50
    än
    0.48
     briefings
    0.48
     review
    0.46
    ier
    0.46
     ஆராய்ச்சி
    0.46
     vacation
    0.45
    men
    0.44
     research
    0.43
    OL
    0.42
    Activations Density 0.012%

    No Known Activations