© 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. 11805
    Prev
    Next
    INDEX
    Explanations

    thresholds, limits, and expectations

    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
    应用程序
    0.42
     दिखाई
    0.42
    नाने
    0.42
     सब्जी
    0.41
    ায়া
    0.41
    辽
    0.40
    购物
    0.39
    展现
    0.39
    影响
    0.39
     özelliği
    0.39
    POSITIVE LOGITS
     threshold
    0.82
     thresholds
    0.80
    threshold
    0.75
     standards
    0.70
     benchmarks
    0.70
     benchmark
    0.68
    基準
    0.67
     expectations
    0.65
     expectation
    0.64
     norm
    0.64
    Activations Density 0.149%

    No Known Activations