© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35282
    Prev
    Next
    INDEX
    Explanations

    to followed by verbs or nouns

    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_22/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
    ća
    -1.04
    Bandwidth
    -0.96
     mantra
    -0.96
     Faces
    -0.96
     it
    -0.95
    だったが
    -0.94
     progressivement
    -0.93
    '
    -0.91
    父の
    -0.91
     Mour
    -0.91
    POSITIVE LOGITS
     you
    2.61
     us
    2.50
     everyone
    1.75
     anyone
    1.70
     readers
    1.62
     me
    1.60
     them
    1.56
     viewers
    1.48
     students
    1.45
     customers
    1.45
    Activations Density 0.069%

    No Known Activations