© 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. 86946
    Prev
    Next
    INDEX
    Explanations

    safety or risk

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

    The neuron is tuned to detect safety‐related terms (especially “safety” and its variants) in the text.

    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
    狴
    -1.48
    ⽰
    -1.44
    tried
    -1.41
    rivial
    -1.40
    provides
    -1.40
     ktoré
    -1.39
     ‘’
    -1.38
    (;;)
    -1.38
     ſaid
    -1.36
    錞
    -1.36
    POSITIVE LOGITS
     when
    1.52
     where
    1.48
    来ました
    1.34
     dergleichen
    1.30
     it
    1.27
    様です
    1.26
    はその
    1.24
    itemize
    1.23
     both
    1.23
     zna
    1.23
    Activations Density 0.028%

    No Known Activations