© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 79439
    Prev
    Next
    INDEX
    Explanations

    technical interpretation and workflows

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on highly technical terms related to three-dimensional seismic imaging and subsurface geologic mapping.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    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
    Negative Logits
     ekolog
    -0.99
    實驗
    -0.91
     spokoj
    -0.85
     Ꮎ
    -0.82
     experimenter
    -0.82
    كيفية
    -0.82
    sieke
    -0.81
     Gläub
    -0.81
     Sunset
    -0.81
    }">
    -0.81
    POSITIVE LOGITS
     honor
    1.12
     interpretation
    1.10
     interpretations
    1.02
     honoring
    1.02
     petro
    1.02
     workflows
    0.99
     honour
    0.99
     workflow
    0.95
     interpreters
    0.94
     interpreter
    0.93
    Activations Density 0.014%

    No Known Activations