© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102881
    Prev
    Next
    INDEX
    Explanations

    so is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     is
    -1.94
    ğlık
    -1.81
    thansa
    -1.74
    degna
    -1.73
    γωγ
    -1.70
    olybdenum
    -1.69
    
    -1.68
    汩
    -1.68
     итого
    -1.66
    嵛
    -1.66
    POSITIVE LOGITS
     our
    2.41
    1
    2.16
    6
    1.98
    3
    1.97
    *
    1.88
     ولی
    1.88
    5
    1.88
    7
    1.77
    9
    1.77
    那我
    1.76
    Activations Density 0.006%

    No Known Activations