© 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. 83322
    Prev
    Next
    INDEX
    Explanations

    GLSL, GLM, GLKit

    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
     परि
    -0.80
     bukti
    -0.76
     Before
    -0.73
     idyl
    -0.72
    geer
    -0.71
    愈
    -0.71
     with
    -0.71
     While
    -0.70
     More
    -0.70
     every
    -0.70
    POSITIVE LOGITS
    wäsche
    0.88
     endroits
    0.85
    赛季
    0.84
     aggregating
    0.84
    Season
    0.84
     hierarch
    0.82
     fontWeight
    0.81
     représenter
    0.81
    orthy
    0.80
     behulp
    0.80
    Activations Density 0.008%

    No Known Activations