© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 4194
    Prev
    Next
    INDEX
    Explanations

    pronoun followed by here

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

    the neuron activates on tokens that occur in the model's (assistant's) output — i.e., it detects tokens appearing in the assistant's responses.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    p
    0.19
    X
    0.19
    IN
    0.19
    td
    0.19
    thing
    0.18
    type
    0.18
    ap
    0.18
    ic
    0.18
    um
    0.18
    CH
    0.18
    POSITIVE LOGITS
    zelf
    0.24
     جميعا
    0.21
     personalmente
    0.20
    ſelf
    0.18
    <unused2127>
    0.18
     personally
    0.18
     Юлия
    0.18
     くれ
    0.17
     deewana
    0.16
     अखिलेश
    0.16
    Activations Density 0.133%

    No Known Activations