© 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. 43667
    Prev
    Next
    INDEX
    Explanations

    low end or high end

    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
    м
    0.86
    ة
    0.80
    ه
    0.80
    sentence
    0.80
    V
    0.80
    IA
    0.79
    4
    0.79
    ٤
    0.78
    ль
    0.78
    ленных
    0.78
    POSITIVE LOGITS
    ,
    1.03
     ότι
    1.00
     अ
    0.93
    ou
    0.92
     îi
    0.91
    aj
    0.90
     únicamente
    0.88
    ’
    0.88
     forecasts
    0.87
    ↵↵
    0.86
    Activations Density 0.007%

    No Known Activations