© 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. 60638
    Prev
    Next
    INDEX
    Explanations

    intensifiers and adverbs

    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
    -2.66
     and
    -2.16
     it
    -2.14
     that
    -1.84
     know
    -1.69
     but
    -1.63
     which
    -1.59
     whose
    -1.55
    S
    -1.55
     to
    -1.52
    POSITIVE LOGITS
    </em>
    1.67
    
    1.66
    ussure
    1.60
    🪆
    1.60
    mickey
    1.59
     temprano
    1.57
     མ
    1.54
     Änderung
    1.51
    
    1.51
    ≲
    1.49
    Activations Density 0.046%

    No Known Activations