© 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. 108247
    Prev
    Next
    INDEX
    Explanations

    mythological figures and paternal concepts

    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
    が起こ
    -0.79
     mond
    -0.78
    fluor
    -0.74
    coran
    -0.74
    akum
    -0.72
     consolation
    -0.71
    ོ་
    -0.70
    🦹
    -0.70
     دور
    -0.69
     Tigers
    -0.69
    POSITIVE LOGITS
    ratos
    1.20
     Blades
    1.00
     Olympus
    0.90
     PlayStation
    0.82
    father
    0.79
    サンタ
    0.78
     Ragnar
    0.77
    Santa
    0.77
    Spartan
    0.77
     dad
    0.75
    Activations Density 0.007%

    No Known Activations