© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117274
    Prev
    Next
    INDEX
    Explanations

    armor and its contexts

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

    The neuron fires on words related to armor and armored protection (e.g. armor, armoured, armor-piercing, reactive armor, 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
     содержа
    -0.93
     edward
    -0.87
     poul
    -0.87
     Salida
    -0.86
     carlos
    -0.82
     alamu
    -0.82
     dacia
    -0.82
     GEST
    -0.81
     Lij
    -0.81
    getError
    -0.81
    POSITIVE LOGITS
     piercing
    1.34
    piercing
    1.28
     Pier
    1.16
    Pier
    0.91
     penetration
    0.91
     plating
    0.89
    plated
    0.85
    rising
    0.84
    clad
    0.82
     of
    0.80
    Activations Density 0.021%

    No Known Activations