© 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. 106474
    Prev
    Next
    INDEX
    Explanations

    blockade

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

    This neuron responds strongly to mentions of armed conflicts and their human‐suffering context, e.g. locations of sieges or wars (Gaza, Gulf War, Iraq) and suffering terms (starvation, disease).

    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
     postpone
    -0.75
     přev
    -0.75
     disappointment
    -0.75
     台中
    -0.73
    ikiran
    -0.72
    ṓ
    -0.72
    mappings
    -0.71
    Follower
    -0.71
    bài
    -0.70
     bílé
    -0.68
    POSITIVE LOGITS
     blockade
    3.69
     block
    2.31
     Block
    2.19
    block
    2.11
     блока
    2.05
    Block
    1.95
     BLOCK
    1.95
     bloqueo
    1.91
    BLOCK
    1.84
     blockage
    1.82
    Activations Density 0.019%

    No Known Activations