© 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. 6087
    Prev
    Next
    INDEX
    Explanations

    the presence of proper names and named entities (e.g. people, places, event titles) in the text.

    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
    http
    1.47
     http
    1.35
    
    1.14
    􀂃
    1.04
     xrange
    1.03
    :-)
    0.93
     XHTML
    0.86
     muß
    0.84
    군요
    0.84
     ব্যাটসম্যান
    0.84
    POSITIVE LOGITS
     TikTok
    3.16
     tiktok
    3.03
     Tiktok
    2.91
    TikTok
    2.83
    🫶
    2.77
    🥹
    2.64
    tiktok
    2.41
     🥰
    2.33
    🫡
    2.30
    🤍
    2.28
    Activations Density 0.527%

    No Known Activations