© 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. 59045
    Prev
    Next
    INDEX
    Explanations

    iSCSI, SOAP, IPsec, capabilities

    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
    getHost
    -1.21
    غا
    -1.13
     was
    -1.13
     extro
    -1.11
     independiente
    -1.10
     in
    -1.10
     intangible
    -1.09
    herstellung
    -1.09
    这是一
    -1.09
     According
    -1.07
    POSITIVE LOGITS
    但不
    1.38
    
    1.34
     soweit
    1.33
    澶
    1.32
     bleiben
    1.29
    핏
    1.28
     dürfte
    1.28
    苾
    1.27
     renovar
    1.26
     acercar
    1.23
    Activations Density 0.014%

    No Known Activations