© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109607
    Prev
    Next
    INDEX
    Explanations

    color depth

    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
    urts
    -0.83
    âteau
    -0.79
     deposits
    -0.77
     trapez
    -0.75
     Chill
    -0.74
    の一つ
    -0.70
     Alexa
    -0.69
     воло
    -0.68
    слен
    -0.68
     []),
    -0.68
    POSITIVE LOGITS
     depth
    1.48
    depth
    1.38
     profundidad
    1.30
     Depth
    1.27
     profondità
    1.26
    Depth
    1.19
     depths
    1.16
     deepen
    1.12
     DEPTH
    1.09
     deep
    1.04
    Activations Density 0.024%

    No Known Activations