© 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. 22-GEMMASCOPE-RES-131K
    7. 73738
    Prev
    Next
    INDEX
    Explanations

    avatar or profile picture

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

    The neuron is specialized to detect tokens referring to user profile pictures or avatars (e.g. “profile,” “avatar,” “photo,” “Image,” “Url”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     explains
    -1.19
    ：「
    -1.16
     it
    -1.15
     $
    -1.10
    onomian
    -1.09
    文物
    -1.09
    ススメ
    -1.05
    atoday
    -1.04
    而出
    -1.04
     explained
    -1.04
    POSITIVE LOGITS
     selfies
    1.20
     profile
    1.18
     персона
    1.11
    cticide
    1.11
     personal
    1.09
    ynchronously
    1.05
    おはよう
    1.04
     perso
    1.03
    profil
    1.02
    standes
    1.01
    Activations Density 0.004%

    No Known Activations