© 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. 102384
    Prev
    Next
    INDEX
    Explanations

    inflict, afflict, inflection

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

    The neuron fires on words related to inflicting or causing harm (e.g. inflict, inflicted, afflict, infliction).

    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
    珢
    -2.63
    síða
    -2.59
    actéristi
    -2.48
    秝
    -2.41
    ፔ
    -2.30
    繽
    -2.25
    父の
    -2.25
    ᚔ
    -2.22
    Ꮷ
    -2.20
    艄
    -2.20
    POSITIVE LOGITS
    ↵
    3.22
    “
    2.77
    .
    2.66
    也
    2.41
    ?"
    2.36
     The
    2.28
     There
    2.16
    ’
    2.14
    1
    2.08
    ")
    2.05
    Activations Density 0.003%

    No Known Activations