© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38562
    Prev
    Next
    INDEX
    Explanations

    new followed by noun

    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
    <bos>
    -2.97
    は
    -2.41
    </strong>
    -2.23
    -
    -2.14
    ⟝
    -2.02
    </h3>
    -2.00
    是最
    -1.94
    </em>
    -1.94
     l
    -1.86
      
    -1.83
    POSITIVE LOGITS
    躥
    2.67
     york
    2.22
     However
    2.19
    慜
    2.08
     zealand
    2.08
    </b>
    2.02
     Recently
    1.96
    
    1.96
    禇
    1.95
    comers
    1.94
    Activations Density 0.100%

    No Known Activations