© 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. 38919
    Prev
    Next
    INDEX
    Explanations

    regional contexts

    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
    🫅
    -2.69
    
    -2.63
     เมื่อ
    -2.45
    Xiv
    -2.44
     This
    -2.44
    𝗟
    -2.41
    
    -2.39
    htb
    -2.33
    躄
    -2.33
    儅
    -2.27
    POSITIVE LOGITS
    3
    3.41
    7
    3.39
    6
    3.34
    5
    3.22
    _
    3.16
    (
    2.98
    4
    2.95
    b
    2.89
    8
    2.88
    0
    2.80
    Activations Density 0.008%

    No Known Activations