© 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. 59622
    Prev
    Next
    INDEX
    Explanations

    conversational interactions

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

    The neuron fires on words referring to conversational interaction (e.g. chat, converse, talk, interact, conversation).

    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
     be
    -1.72
    </h2>
    -1.70
     of
    -1.44
    ↵
    -1.41
     originate
    -1.38
     traditionelle
    -1.38
     كيفية
    -1.37
    </sup>
    -1.32
     misschien
    -1.27
    皛
    -1.27
    POSITIVE LOGITS
     about
    1.98
    主な
    1.40
    ia
    1.38
    برة
    1.37
    ative
    1.37
     with
    1.30
     Schulze
    1.30
    "--
    1.29
    ៍
    1.28
    俺は
    1.27
    Activations Density 0.034%

    No Known Activations