© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40168
    Prev
    Next
    INDEX
    Explanations

    computing results

    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
    pasti
    -1.55
     มัน
    -1.49
     hanya
    -1.48
    only
    -1.47
     فقط
    -1.39
    
    -1.37
     съдържа
    -1.37
    렷
    -1.35
    靦
    -1.34
     tylko
    -1.32
    POSITIVE LOGITS
     for
    1.84
     sometimes
    1.63
    h
    1.43
    0
    1.41
    </h2>
    1.38
    c
    1.34
     more
    1.32
     if
    1.31
     often
    1.31
     when
    1.27
    Activations Density 0.008%

    No Known Activations