© 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. 22-GEMMASCOPE-RES-131K
    7. 65513
    Prev
    Next
    INDEX
    Explanations

    own pace

    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
     åren
    -1.49
    шип
    -1.21
    eltjes
    -1.11
    kinh
    -1.09
    𝒙
    -1.09
     äldre
    -1.09
     in
    -1.07
     arbeta
    -1.05
    cznego
    -1.02
     насеља
    -1.02
    POSITIVE LOGITS
     everyone
    1.29
     viewHolder
    1.27
    λαμβ
    1.25
    最後
    1.16
    breviations
    1.16
     moments
    1.14
     funcionalidad
    1.13
    ૉ
    1.13
     everyday
    1.12
     usados
    1.12
    Activations Density 0.048%

    No Known Activations