© 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. 34-GEMMASCOPE-RES-131K
    7. 77098
    Prev
    Next
    INDEX
    Explanations

    all-wheel drive

    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
    ᚦ
    -0.89
     MEDIC
    -0.82
     |]
    -0.81
     フレーム
    -0.80
     Schroeder
    -0.79
    gazione
    -0.79
    😲
    -0.78
     hispan
    -0.78
     cigars
    -0.77
    ग्री
    -0.77
    POSITIVE LOGITS
     Apple
    1.70
     Android
    1.41
    Apple
    1.29
     adaptive
    1.24
     LED
    1.24
     wireless
    1.15
     android
    1.11
     climate
    1.09
     Qi
    1.06
     Adaptive
    1.05
    Activations Density 0.009%

    No Known Activations