© 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. 72469
    Prev
    Next
    INDEX
    Explanations

    deadly + harmful events

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

    The neuron specifically looks for the word "deadly" appearing in text.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    (
    -2.73
    ar
    -2.44
    ers
    -2.41
    ?
    -2.34
    '
    -2.34
    \
    -2.16
    ፨
    -2.14
    N
    -2.13
    ans
    -2.11
    </sub>
    -2.08
    POSITIVE LOGITS
    他的
    2.41
    ŚĆ
    2.19
    簟
    2.14
     besta
    2.11
    鸶
    2.05
     خواهند
    2.03
     Générale
    2.03
     сист
    2.03
    鵟
    2.02
    visionnement
    2.00
    Activations Density 0.005%

    No Known Activations