© 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. 92143
    Prev
    Next
    INDEX
    Explanations

    often see, is when, mimic the, would be

    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
    号码
    0.51
     Sofia
    0.50
     Garant
    0.50
    的任务
    0.49
     Neolithic
    0.49
    Задача
    0.49
    癥
    0.48
    地址
    0.47
     والدین
    0.47
    的感觉
    0.47
    POSITIVE LOGITS
    _
    0.62
     engage
    0.52
    hist
    0.46
     troubled
    0.45
     during
    0.44
     becom
    0.44
     activate
    0.44
    /
    0.44
     hear
    0.43
     onset
    0.43
    Activations Density 0.002%

    No Known Activations