© 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. 57968
    Prev
    Next
    INDEX
    Explanations

    mesh and grid

    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
    тт
    -0.85
    moy
    -0.81
    لاک
    -0.75
    시오
    -0.74
     می‌باشد
    -0.70
     безо
    -0.70
     internacionais
    -0.70
     namorado
    -0.69
    gorod
    -0.68
    Maw
    -0.68
    POSITIVE LOGITS
     mesh
    1.76
    mesh
    1.35
     grid
    1.33
     Mesh
    1.30
    MESH
    1.20
     MES
    1.18
    grid
    1.17
    Mesh
    1.11
     grids
    1.00
     Grid
    0.93
    Activations Density 0.015%

    No Known Activations