© 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. 25668
    Prev
    Next
    INDEX
    Explanations

    interrogative structures

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

    question followed by colon

    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
    able
    0.50
    p
    0.47
     to
    0.46
    ished
    0.46
     Mere
    0.46
     Rech
    0.45
     by
    0.44
    imated
    0.43
     सक्षम
    0.42
    ဆေး
    0.42
    POSITIVE LOGITS
    ג
    0.47
    ಿಸ
    0.47
     اللَّ
    0.47
    شكال
    0.46
     أنّ
    0.46
     createElement
    0.44
     그러니까
    0.44
    ْر
    0.44
    拍摄
    0.44
     pregunt
    0.44
    Activations Density 0.002%

    No Known Activations