© 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. 92043
    Prev
    Next
    INDEX
    Explanations

    network chains or headers

    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
    ñon
    -0.76
    ților
    -0.75
     abandonné
    -0.71
     Bauch
    -0.70
    GLFW
    -0.69
     tiled
    -0.69
    ﮐ
    -0.69
    rrggbb
    -0.68
    obes
    -0.68
    zd
    -0.67
    POSITIVE LOGITS
    nat
    0.99
     nat
    0.93
     chains
    0.88
     chaînes
    0.79
     masquer
    0.78
     chaîne
    0.77
     Chains
    0.76
    COMMIT
    0.75
     NAT
    0.74
    Chains
    0.74
    Activations Density 0.041%

    No Known Activations