© 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. 16-GEMMASCOPE-2-RES-262K
    7. 29478
    Prev
    Next
    INDEX
    Explanations

    linked list

    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_16_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
    开心
    0.62
    。
    0.57
    东
    0.55
     using
    0.54
     samen
    0.54
     utilizzando
    0.54
    ad
    0.54
     supplier
    0.54
     transporting
    0.53
     vorg
    0.53
    POSITIVE LOGITS
    DTD
    0.80
    σε
    0.63
    G
    0.59
    olph
    0.58
    J
    0.56
    مہ
    0.56
    スの
    0.55
    ]^{+}$
    0.55
    Z
    0.55
    که
    0.54
    Activations Density 0.000%

    No Known Activations