© 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. 201559
    Prev
    Next
    INDEX
    Explanations

    connectors and structure

    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
     despicable
    0.45
    sn
    0.43
    龌
    0.40
    snp
    0.40
     compañías
    0.39
    ROME
    0.39
    ibs
    0.39
     ομάδα
    0.39
    -
    0.38
    за
    0.38
    POSITIVE LOGITS
    reszt
    0.51
    গাঁ
    0.47
    শাস্ত্র
    0.46
     autophagy
    0.46
     veil
    0.45
    সই
    0.44
     اندراج
    0.44
    ⼤
    0.44
    ㄾ
    0.43
     ткань
    0.43
    Activations Density 0.001%

    No Known Activations