© 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. 32052
    Prev
    Next
    INDEX
    Explanations

    covered or surrounded

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

    This neuron detects technical component and material nouns (like “core,” “cells,” “pad,” “wafer,” etc.) in scientific or patent‐style descriptions.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     contiennent
    -0.80
    madi
    -0.79
    xdb
    -0.78
    erías
    -0.76
    を外
    -0.76
     mutated
    -0.75
     Austausch
    -0.74
     otwar
    -0.74
    tiéndose
    -0.72
     Gesetz
    -0.71
    POSITIVE LOGITS
     covered
    5.06
    covered
    3.92
    Covered
    3.89
     Covered
    3.84
     COVER
    2.64
     surrounded
    2.53
     покры
    2.52
    COVER
    2.45
     pokry
    2.34
     cover
    2.33
    Activations Density 0.130%

    No Known Activations