© 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. 9356
    Prev
    Next
    INDEX
    Explanations

    acting, pretense, or playing roles

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

    The neuron flags words and phrases related to performing or role‐playing (e.g. “act,” “acting,” “play,” “actors”).

    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
     TÉCNICA
    -1.76
    ଃ
    -1.70
     حتی
    -1.56
     TÉCN
    -1.45
    ſtre
    -1.39
     Theorems
    -1.38
    thansa
    -1.37
    _{
    -1.36
     Aún
    -1.28
    
    -1.28
    POSITIVE LOGITS
    uevas
    1.22
    𝕤
    1.19
    appropriate
    1.19
     not
    1.18
    が出来
    1.17
    猻
    1.17
     všetky
    1.14
     gevonden
    1.13
     appropriate
    1.13
    各样的
    1.13
    Activations Density 0.051%

    No Known Activations