© 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. 31770
    Prev
    Next
    INDEX
    Explanations

    rubble and ruins

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

    The neuron fires on words describing physical destruction debris and remnants—rubble, wreckage, debris, ruins, etc.

    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
    Ār
    -0.94
     komen
    -0.82
     preparados
    -0.82
    錮
    -0.82
     solução
    -0.81
    резать
    -0.79
    夜は
    -0.79
    ÊNCIAS
    -0.78
    drawSprites
    -0.78
     drenaje
    -0.77
    POSITIVE LOGITS
     debris
    3.11
     wreckage
    2.67
     rubble
    2.58
     ruins
    2.33
     remnants
    2.31
     remains
    2.00
     Debris
    2.00
     fragments
    1.86
    残
    1.77
     aftermath
    1.75
    Activations Density 0.063%

    No Known Activations