© 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. 3510
    Prev
    Next
    INDEX
    Explanations

    The neuron detects tokens that are part of book or publication titles.

    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
    !:
    0.80
    !;
    0.76
    :
    0.75
    ':
    0.67
    !
    0.66
    ?:
    0.65
    |
    0.64
    !,
    0.64
    !-
    0.63
    *;
    0.63
    POSITIVE LOGITS
     futurs
    0.66
     soldats
    0.66
     autoestima
    0.64
     rejoindre
    0.63
     ansvar
    0.62
     perdagangan
    0.62
     confianza
    0.61
     desiderio
    0.61
     tropas
    0.60
     perks
    0.60
    Activations Density 0.004%

    No Known Activations