© 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. 12962
    Prev
    Next
    INDEX
    Explanations

    “said” or “says” followed by pronoun

    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
    ALSO
    -1.09
     OGSÅ
    -1.07
    ggak
    -1.03
    itern
    -1.02
     ALSO
    -0.98
     Fragen
    -0.96
    примеча
    -0.93
     TAMBÉM
    -0.93
     também
    -0.93
    antiago
    -0.93
    POSITIVE LOGITS
     they
    1.38
     it
    1.29
     she
    1.15
     them
    1.13
     him
    1.04
    ệu
    1.01
    ihin
    0.97
    например
    0.96
    様々
    0.95
     there
    0.94
    Activations Density 0.005%

    No Known Activations