© 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. 91868
    Prev
    Next
    INDEX
    Explanations

    container rim or opening

    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
    arki
    -0.79
     Longitud
    -0.77
    實現
    -0.76
    endpoints
    -0.75
     paquet
    -0.74
     finales
    -0.73
    vaient
    -0.72
    lengths
    -0.71
     degré
    -0.71
    avigation
    -0.70
    POSITIVE LOGITS
     sides
    2.17
     rim
    2.11
     walls
    2.06
     Walls
    1.58
    sides
    1.56
     Sides
    1.53
     rims
    1.51
     lip
    1.50
     paredes
    1.42
    walls
    1.41
    Activations Density 0.077%

    No Known Activations