© 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. 34-GEMMASCOPE-RES-131K
    7. 93599
    Prev
    Next
    INDEX
    Explanations

    Red Bull Racing and license notices

    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
     duration
    -0.75
     aggregate
    -0.71
    xFC
    -0.70
    Javascript
    -0.68
     ruby
    -0.68
     Depression
    -0.67
    cracker
    -0.66
    ün
    -0.65
    Depression
    -0.65
     förs
    -0.65
    POSITIVE LOGITS
    CardContent
    0.76
    wirkungen
    0.75
     생성
    0.73
     homeward
    0.72
     delegations
    0.69
     embassies
    0.69
    Karten
    0.69
    tività
    0.69
     esperienza
    0.67
    arget
    0.66
    Activations Density 0.068%

    No Known Activations