© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100800
    Prev
    Next
    INDEX
    Explanations

    alive, dead, viability

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

    words related to biological viability, life status, or health state.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron responds to terms denoting life‐or‐death or viability states (e.g. alive, dead, kill, viability).

    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
     outpost
    -1.56
    irinha
    -1.52
    茈
    -1.45
     necesitan
    -1.43
    ')
    -1.41
    gendes
    -1.41
     ')
    -1.41
    versaire
    -1.41
    </code>
    -1.41
    рования
    -1.41
    POSITIVE LOGITS
    .
    1.56
     on
    1.43
    Two
    1.43
     Почему
    1.36
    Three
    1.34
     softly
    1.34
         
    1.31
     you
    1.30
     hábito
    1.29
     estimado
    1.27
    Activations Density 0.059%

    No Known Activations