© 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. 40144
    Prev
    Next
    INDEX
    Explanations

    shall followed by verb

    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
     of
    -1.80
    with
    -1.70
     didn
    -1.64
     doesn
    -1.63
     ''
    -1.62
     každý
    -1.61
    はこの
    -1.61
    Smiling
    -1.59
     sehingga
    -1.59
     musíte
    -1.56
    POSITIVE LOGITS
    .”
    1.77
    .")]
    1.72
    . 
    1.62
    <bos>
    1.59
     
    1.59
     cliché
    1.50
    …’
    1.45
    spo
    1.44
    lgari
    1.44
     
    1.42
    Activations Density 0.010%

    No Known Activations