© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 40121
    Prev
    Next
    INDEX
    Explanations

    personal pronouns expressing actions

    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
     "
    -1.05
    A
    -0.96
     herbe
    -0.93
    L
    -0.91
     vocale
    -0.91
    catchError
    -0.90
     D
    -0.90
     financiar
    -0.90
     использовать
    -0.89
    psin
    -0.88
    POSITIVE LOGITS
     then
    1.38
     verhaal
    1.34
     stratég
    1.30
     szükség
    1.26
     circunstancia
    1.23
     bahía
    1.20
    Abbildung
    1.18
     lámpara
    1.16
     secuencia
    1.16
    着了
    1.13
    Activations Density 0.070%

    No Known Activations