© 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. 99556
    Prev
    Next
    INDEX
    Explanations

    electrical wires and grounding

    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
    鎵
    -0.84
    mazoo
    -0.83
    Electrical
    -0.83
     mourut
    -0.82
    atoon
    -0.81
     reuni
    -0.80
     anhydrous
    -0.80
    werken
    -0.80
    ξα
    -0.80
    wali
    -0.79
    POSITIVE LOGITS
     coming
    1.08
     constant
    0.96
     wires
    0.81
     goes
    0.77
     from
    0.77
     going
    0.74
     continuous
    0.74
     lmfao
    0.72
     on
    0.72
     Coming
    0.71
    Activations Density 0.011%

    No Known Activations