© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6337
    Prev
    Next
    INDEX
    Explanations

    clickbait titles and phrases

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

    This neuron fires on the “of” in multi‐word proper names—most notably in “Gulf of X” place names (and similarly in “View attachment”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ETC
    0.57
     colaborador
    0.55
    屓
    0.55
     عضو
    0.53
     Mem
    0.53
     पीछ
    0.52
    }$:
    0.52
     anggota
    0.51
     membro
    0.51
     ISR
    0.51
    POSITIVE LOGITS
    View
    0.59
    箓
    0.59
     View
    0.56
    Click
    0.54
     click
    0.54
    એ
    0.52
    clicks
    0.52
     clicks
    0.52
     gesagt
    0.50
    Loading
    0.50
    Activations Density 0.007%

    No Known Activations