© 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. 75724
    Prev
    Next
    INDEX
    Explanations

    code comments with @param

    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
     million
    -0.86
    jian
    -0.84
      “
    -0.84
    crollView
    -0.84
    受益
    -0.83
     communicates
    -0.82
    ården
    -0.81
    providedIn
    -0.80
    𝟔
    -0.78
     bericht
    -0.77
    POSITIVE LOGITS
     @
    1.74
    @
    1.27
    param
    1.21
     param
    1.05
    (@
    0.95
    >@
    0.95
    @\
    0.93
    ,@
    0.92
     NOTE
    0.85
     (@
    0.84
    Activations Density 0.014%

    No Known Activations