© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 11223
    Prev
    Next
    INDEX
    Explanations

    underlying information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Buenas
    0.46
    TERN
    0.45
    照明
    0.44
    (
    0.43
    voll
    0.43
     glare
    0.43
    вел
    0.43
    <!
    0.42
     ד
    0.42
    
    0.41
    POSITIVE LOGITS
    工程师
    0.47
     Schuyler
    0.46
     Clayton
    0.45
     Lyman
    0.45
     McIntyre
    0.45
     Prescott
    0.45
     لیا
    0.45
     Committee
    0.44
     Nantucket
    0.44
     Houghton
    0.43
    Activations Density 0.003%

    No Known Activations