© 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. 24-GEMMASCOPE-2-RES-16K
    7. 8208
    Prev
    Next
    INDEX
    Explanations

    the fact that

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

    The neuron primarily detects occurrences of the word “fact.”

    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_24_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
    i
    1.25
    ه
    1.14
     וכ
    1.13
    ে
    1.12
    AN
    1.09
    ｉ
    1.06
    }}$
    1.00
     ihe
    0.99
    𝗔
    0.95
     pengertian
    0.95
    POSITIVE LOGITS
    یکه
    1.39
    ளைஞ
    1.32
     Tatsache
    1.29
    상
    1.29
     kwamba
    1.21
    ل
    1.21
     saill
    1.19
    zione
    1.09
    ដែល
    1.09
    ت
    1.07
    Activations Density 0.007%

    No Known Activations