© 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. 10-GEMMASCOPE-RES-131K
    7. 41855
    Prev
    Next
    INDEX
    Explanations

    and followed by various 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_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
     this
    -2.28
     convencer
    -1.38
    selbe
    -1.36
    ⍟
    -1.33
     '_'
    -1.33
     Septembre
    -1.30
    setLayoutManager
    -1.30
    瑨
    -1.30
     our
    -1.29
     листья
    -1.28
    POSITIVE LOGITS
    8
    1.57
    ,”
    1.55
     —
    1.51
    )
    1.48
    ?
    1.38
    =
    1.38
     be
    1.35
      
    1.34
     to
    1.30
        
    1.28
    Activations Density 0.112%

    No Known Activations