© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 92178
    Prev
    Next
    INDEX
    Explanations

    code, logic, functions, loops

    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
    il
    0.43
    ធម្ម
    0.42
    ie
    0.42
     still
    0.41
     inland
    0.41
    ają
    0.40
    appi
    0.38
     w
    0.38
    వ్వ
    0.38
    listed
    0.38
    POSITIVE LOGITS
     Fibonacci
    0.47
    燔
    0.45
    旋转
    0.42
    ждая
    0.41
     circularly
    0.41
    setInterval
    0.39
     matematica
    0.38
    Tìm
    0.38
     triángulo
    0.38
    递归
    0.38
    Activations Density 0.035%

    No Known Activations