© 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. 864
    Prev
    Next
    INDEX
    Explanations

    The neuron is specifically detecting the surname “Knaup.”

    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
    =
    0.43
    は
    0.42
    นิ
    0.40
     là
    0.39
     canonical
    0.39
    ]);
    0.39
    ]=
    0.38
    ]
    0.38
    คือ
    0.38
    )
    0.37
    POSITIVE LOGITS
     Furthermore
    0.50
     Undoubtedly
    0.50
    payers
    0.49
     Initiatives
    0.49
     Además
    0.48
     Inoltre
    0.48
     Supporters
    0.46
     Although
    0.46
     Moreover
    0.46
     Also
    0.46
    Activations Density 0.000%

    No Known Activations