© 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. 19397
    Prev
    Next
    INDEX
    Explanations

    list separation

    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
     bactéries
    0.45
     वैज्ञानिकों
    0.42
     investigators
    0.42
    ل
    0.41
     catégories
    0.40
     evidences
    0.39
     elucid
    0.39
     scientifiques
    0.39
    拡散方程式
    0.39
    لی
    0.38
    POSITIVE LOGITS
    StdHandle
    0.53
    náv
    0.49
    a
    0.49
    c
    0.49
    r
    0.47
     Monroe
    0.47
     生活
    0.44
     Donuts
    0.44
    hok
    0.44
     Commerce
    0.43
    Activations Density 0.000%

    No Known Activations