© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70885
    Prev
    Next
    INDEX
    Explanations

    to survive

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

    The neuron specializes in detecting occurrences of the root “survive” (as in “survive” or “survival”).

    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
    氿
    -2.09
     ſy
    -1.95
    祼
    -1.83
     kijk
    -1.78
    莚
    -1.75
     Spanyol
    -1.74
    âmetro
    -1.72
    '
    -1.69
     kaksi
    -1.63
    好看的
    -1.63
    POSITIVE LOGITS
     not
    2.09
     Not
    1.91
     survive
    1.84
     With
    1.84
     also
    1.81
     Isn
    1.81
     Few
    1.75
     on
    1.73
     In
    1.71
    呖
    1.69
    Activations Density 0.010%

    No Known Activations