© 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. 112893
    Prev
    Next
    INDEX
    Explanations

    Safety and Efficacy

    np_acts-logits-general · gemini-2.5-flash-lite

    programming code related to Minecraft, particularly imports and package declarations.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    {
    -1.89
    </h4>
    -1.87
    }
    -1.80
    e
    -1.73
    '
    -1.67
    .'
    -1.66
    ">
    -1.66
    <strong>
    -1.65
    ',
    -1.64
     At
    -1.60
    POSITIVE LOGITS
     Vainqueur
    1.70
     lunghi
    1.69
    廔
    1.66
    ियर
    1.63
    
    1.63
    茈
    1.57
     vierte
    1.52
     assai
    1.52
    㩒
    1.51
     撮り
    1.50
    Activations Density 0.007%

    No Known Activations