© 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. 66457
    Prev
    Next
    INDEX
    Explanations

    quantitative values

    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
    ?”
    -1.98
    }
    -1.93
     Ağ
    -1.64
     "
    -1.62
    リーナ
    -1.56
     ?”
    -1.53
    ]={
    -1.50
    ")==
    -1.45
     Reſ
    -1.45
     {
    -1.44
    POSITIVE LOGITS
     também
    1.73
     также
    1.58
     wydaje
    1.48
     więks
    1.47
    er
    1.47
    
    1.44
     qualquer
    1.41
     również
    1.40
     salvaje
    1.40
     berücksich
    1.39
    Activations Density 0.053%

    No Known Activations