© 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. 22-GEMMASCOPE-RES-131K
    7. 26598
    Prev
    Next
    INDEX
    Explanations

    tokens following specific punctuation or short words

    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
     and
    -1.27
     or
    -1.21
     sözler
    -1.16
    ᝰ
    -1.15
    dpa
    -1.09
    Algunas
    -1.09
     стаття
    -1.08
    Ventajas
    -1.08
     bawat
    -1.08
    ächt
    -1.07
    POSITIVE LOGITS
     declarat
    1.08
     ș
    1.05
    ↵↵
    1.02
    ฑ
    1.02
     canadienne
    1.01
    呶
    1.01
     olio
    1.00
    
    0.99
     む
    0.98
     اکنون
    0.98
    Activations Density 0.000%

    No Known Activations