© 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. 34-GEMMASCOPE-RES-131K
    7. 90908
    Prev
    Next
    INDEX
    Explanations

    sentence end punctuation

    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_34/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
    ковые
    -1.26
    })()
    -1.06
    ままで
    -1.05
    ținut
    -1.05
     nho
    -1.01
     voyageurs
    -1.00
     bättre
    -0.98
     acides
    -0.98
    ➃
    -0.98
     châ
    -0.97
    POSITIVE LOGITS
     it
    2.47
     even
    2.45
     if
    2.03
     since
    1.84
     although
    1.78
     there
    1.77
     because
    1.73
     Even
    1.73
    Even
    1.64
     It
    1.59
    Activations Density 0.007%

    No Known Activations