© 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. 60541
    Prev
    Next
    INDEX
    Explanations

    sender label or variable

    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
     was
    -3.16
    v
    -3.13
    ,"
    -3.00
    j
    -2.64
    </h4>
    -2.61
    and
    -2.53
    という感じ
    -2.53
    e
    -2.50
     Schlafzimmer
    -2.47
    {
    -2.42
    POSITIVE LOGITS
    骓
    2.84
    諼
    2.78
     髪型
    2.78
    
    2.69
     Siehe
    2.58
     发型
    2.55
    袮
    2.44
    趼
    2.44
     faciliter
    2.42
    Ꮉ
    2.36
    Activations Density 0.004%

    No Known Activations