© 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. 1375
    Prev
    Next
    INDEX
    Explanations

    causes of failures or damage

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

    The neuron is tuned to spotting mentions of different types of damage or hazards (e.g. categories of property damage).

    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
    Destroy
    -0.87
     raping
    -0.87
    かっこ
    -0.86
    つまみ
    -0.84
    世話
    -0.83
     Proble
    -0.83
    lages
    -0.82
     Throws
    -0.82
    jaciół
    -0.81
     penderita
    -0.81
    POSITIVE LOGITS
     mechanical
    1.28
     sudden
    1.11
     caused
    1.09
     theft
    1.06
    人为
    1.05
     thermal
    1.05
     falling
    1.05
     chemical
    1.05
     fire
    1.04
     physical
    1.04
    Activations Density 0.085%

    No Known Activations