© 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. 34-GEMMASCOPE-RES-131K
    7. 78190
    Prev
    Next
    INDEX
    Explanations

    continue to

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

    This neuron responds to references to social media activity and posts (e.g. mentions of social media, posting, tweeting, accounts, and related terms).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    駅前
    -1.03
    ichu
    -1.02
    駅の
    -0.98
    🏻
    -0.97
     کرب
    -0.97
     focussed
    -0.96
     ecuator
    -0.94
     religieux
    -0.92
    🏼
    -0.91
     любых
    -0.91
    POSITIVE LOGITS
    🏾
    1.34
    African
    1.23
     melanin
    1.06
    ℚ
    1.05
     matric
    1.04
    动漫
    1.03
    Philadelphia
    0.98
    私が
    0.96
     Essence
    0.95
     Sank
    0.95
    Activations Density 0.210%

    No Known Activations