© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38898
    Prev
    Next
    INDEX
    Explanations

    citation mark

    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
     has
    -1.81
     and
    -1.78
    \
    -1.60
     it
    -1.57
    </i>
    -1.55
    </strong>
    -1.52
     planas
    -1.50
    </h3>
    -1.44
                    
    -1.42
    ？」
    -1.37
    POSITIVE LOGITS
    Hmmm
    1.94
    Somehow
    1.74
    也只是
    1.71
    2
    1.70
     reveló
    1.70
    mainly
    1.63
     pomysł
    1.60
     amazing
    1.60
     egentlig
    1.59
    僱
    1.55
    Activations Density 0.001%

    No Known Activations