© 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. 2777
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on the interrogative “where.”

    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
    Macro
    0.77
    солю
    0.76
    Ри
    0.75
    LayoutInflater
    0.71
    Kau
    0.71
    €“
    0.70
    сю
    0.69
    DbContext
    0.68
    Publish
    0.68
     باش
    0.68
    POSITIVE LOGITS
    fler
    0.85
    onek
    0.76
     Siddh
    0.75
     nást
    0.73
    ų
    0.73
    arek
    0.73
     birçok
    0.73
     Giveen
    0.72
    ljiv
    0.71
     informacji
    0.71
    Activations Density 0.000%

    No Known Activations