© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 47039
    Prev
    Next
    INDEX
    Explanations

    machine learning, GGML

    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
    to
    1.03
    u
    0.86
     (
    0.83
    아
    0.82
    ა
    0.82
    an
    0.81
    ان
    0.80
    1
    0.79
    我们
    0.78
    ı
    0.78
    POSITIVE LOGITS
     然後
    0.77
    }/>
    0.73
     優
    0.65
     attham
    0.64
     MAS
    0.63
     CORPER
    0.63
    ด
    0.63
    ד
    0.63
     ELECTRICAL
    0.63
     הת
    0.61
    Activations Density 0.001%

    No Known Activations