© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 36344
    Prev
    Next
    INDEX
    Explanations

    code punctuation and block starts

    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
     POSSIBLE
    -1.11
     kado
    -1.05
    まずは
    -0.97
     potensi
    -0.97
    跸
    -0.96
     universite
    -0.95
     edel
    -0.94
     varm
    -0.94
    ৷
    -0.94
     maa
    -0.93
    POSITIVE LOGITS
     also
    1.28
     there
    1.15
     también
    1.14
     at
    1.12
     or
    1.08
     after
    1.06
     additional
    1.01
     by
    1.00
     use
    1.00
     também
    0.98
    Activations Density 0.002%

    No Known Activations