© 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. 10-GEMMASCOPE-RES-131K
    4. 90415
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by verbs

    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_10/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
     که
    -1.41
    ğına
    -1.27
    ));
    
    -1.23
    vices
    -1.23
    }]$
    -1.20
    ercises
    -1.20
     Einwilligung
    -1.18
     不锈钢
    -1.18
    ,"\
    -1.17
    '));
    -1.16
    POSITIVE LOGITS
     probably
    1.48
     because
    1.36
     M
    1.30
     likely
    1.30
     by
    1.30
     on
    1.29
     F
    1.28
     this
    1.26
     started
    1.26
     A
    1.25
    Activations Density 0.016%

    No Known Activations