© 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. 22-GEMMASCOPE-RES-131K
    7. 39165
    Prev
    Next
    INDEX
    Explanations

    Metadata, Services, Assessing

    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_22/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
     then
    -1.41
    ˂
    -1.12
     lakini
    -1.06
    ♣
    -1.05
    eclamp
    -1.04
    ❣️
    -1.03
    
    -1.02
    moles
    -1.02
     يول
    -1.02
     of
    -1.02
    POSITIVE LOGITS
    なるべく
    1.27
     limitaciones
    1.21
    できるだけ
    1.16
     Eigentümer
    1.13
    外部链接
    1.12
    푉
    1.12
     posibilidades
    1.11
     vieler
    1.08
     adecuados
    1.08
     irgend
    1.06
    Activations Density 0.003%

    No Known Activations