© 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. 31429
    Prev
    Next
    INDEX
    Explanations

    deep, upper, highest, or inner states

    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
    在前
    -0.81
     credito
    -0.80
     sopra
    -0.78
    leriyle
    -0.77
     preferred
    -0.77
    視野
    -0.75
    ässä
    -0.74
    canonical
    -0.73
     EVERYTHING
    -0.73
     view
    -0.73
    POSITIVE LOGITS
     depths
    3.83
     deepest
    2.48
     recesses
    2.34
     depth
    2.33
     bowels
    2.20
     глуби
    2.16
    depth
    2.06
    Depth
    2.03
     deep
    2.00
     DEPTH
    1.98
    Activations Density 0.048%

    No Known Activations