© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68059
    Prev
    Next
    INDEX
    Explanations

    reflexive pronouns and sequences

    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
    aol
    -0.80
    tructuring
    -0.80
    шению
    -0.77
    мания
    -0.75
     @_
    -0.73
    setDisable
    -0.73
    갈
    -0.71
    ഡ
    -0.71
    Xiv
    -0.71
    inario
    -0.71
    POSITIVE LOGITS
     itself
    1.88
     wiederum
    1.61
    itself
    1.59
     themselves
    1.42
    themselves
    1.23
     Itself
    1.21
    本身
    1.18
    さらに
    1.16
     himself
    1.12
     herself
    1.10
    Activations Density 0.155%

    No Known Activations