© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 86550
    Prev
    Next
    INDEX
    Explanations

    adverb followed by action

    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
     was
    -2.41
     there
    -2.22
    </h3>
    -2.13
     itſelf
    -1.73
     and
    -1.73
    because
    -1.70
    ).”
    -1.70
    '></
    -1.67
    ?!”
    -1.67
    ,”
    -1.66
    POSITIVE LOGITS
     been
    4.25
    /*"
    2.08
    峮
    2.03
    //"
    1.98
    ᪥
    1.95
     apologised
    1.91
    
    1.88
    providedIn
    1.87
    endforeach
    1.82
     bestimmten
    1.81
    Activations Density 0.065%

    No Known Activations