© 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. 72163
    Prev
    Next
    INDEX
    Explanations

    topics like religious affairs and Jesuits

    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
     you
    -2.11
    ansvar
    -1.61
     your
    -1.55
    obrá
    -1.55
    Моя
    -1.49
    Recently
    -1.44
    Kommentare
    -1.44
    ＝＝
    -1.43
     mää
    -1.41
    Crítica
    -1.38
    POSITIVE LOGITS
     had
    1.44
    暧
    1.34
     later
    1.32
     after
    1.31
     became
    1.30
     began
    1.30
    取り付け
    1.25
     remained
    1.24
    하였다
    1.24
     did
    1.23
    Activations Density 0.047%

    No Known Activations