© 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-16K
    7. 5592
    Prev
    Next
    INDEX
    Explanations

    numbers, currency symbols, and units

    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_16k_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
     сне
    0.54
    <0x9C>
    0.53
    ו
    0.52
    }\
    0.49
     tuyến
    0.48
    ז
    0.48
    
    0.46
     시
    0.46
     требуют
    0.46
    р
    0.46
    POSITIVE LOGITS
     Scalar
    0.46
     created
    0.44
     Measured
    0.43
    私は
    0.43
     Elegant
    0.42
     Personalized
    0.42
    ]$,
    0.41
     Structural
    0.41
    csc
    0.41
    atie
    0.41
    Activations Density 0.113%

    No Known Activations