© 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. 10-GEMMASCOPE-RES-131K
    7. 7669
    Prev
    Next
    INDEX
    Explanations

    the word die

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

    The neuron activates specifically on the word “die,” i.e. mentions of dying.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    am
    -2.89
    n
    -2.80
    are
    -2.53
     cuyas
    -2.44
    their
    -2.44
     sorprend
    -2.41
    ll
    -2.36
    妞
    -2.34
     .
    -2.34
    r
    -2.28
    POSITIVE LOGITS
     With
    3.11
    }
    2.67
     lampada
    2.52
    手机
    2.42
     spagnolo
    2.41
     crescere
    2.34
     patrie
    2.25
     saluti
    2.17
     occhiali
    2.16
     chirurgie
    2.14
    Activations Density 0.009%

    No Known Activations