© 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. 31901
    Prev
    Next
    INDEX
    Explanations

    going deeper into something

    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
     stark
    -0.96
     dientes
    -0.91
    大致
    -0.89
     aloft
    -0.88
    Endpoints
    -0.86
    efit
    -0.86
    总体
    -0.85
     здра
    -0.83
     faudrait
    -0.83
     overhead
    -0.81
    POSITIVE LOGITS
    depth
    1.03
     depth
    0.97
     into
    0.94
     understanding
    0.92
     layers
    0.91
     Mariana
    0.91
     analysis
    0.88
     fryer
    0.86
     profundidad
    0.85
     wells
    0.85
    Activations Density 0.027%

    No Known Activations