© 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. 10-GEMMASCOPE-RES-131K
    7. 14530
    Prev
    Next
    INDEX
    Explanations

    modal verbs followed by be

    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
     dring
    -1.40
    𐌸
    -1.29
     künftig
    -1.28
    
    -1.27
    Febru
    -1.27
    饽
    -1.26
     ...,
    -1.24
     fenô
    -1.23
    ,''
    -1.20
     ..........
    -1.20
    POSITIVE LOGITS
    ↵
    1.42
     with
    1.41
     игрушка
    1.40
    }
    1.38
    那些
    1.35
    2
    1.33
    We
    1.32
     Töchter
    1.23
    紲
    1.20
    no
    1.20
    Activations Density 0.157%

    No Known Activations