© 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. 70964
    Prev
    Next
    INDEX
    Explanations

    multilingual fragments

    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
    <bos>
    -2.20
    </em>
    -1.80
    
    -1.74
    媪
    -1.68
     considerada
    -1.65
     promove
    -1.60
     gleiche
    -1.58
     другими
    -1.57
     verschillende
    -1.55
     wodurch
    -1.55
    POSITIVE LOGITS
     Each
    1.81
    Also
    1.68
    Beskrivning
    1.67
    There
    1.65
     作り方
    1.57
     tertentu
    1.54
    ㅐ
    1.50
     bidra
    1.48
    见的
    1.46
    (["
    1.45
    Activations Density 0.047%

    No Known Activations