© 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. 3458
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on individual content‐bearing words—i.e. relatively uncommon, domain‐specific nouns or verbs—while ignoring common function words.

    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
     durchaus
    0.86
     র
    0.84
     Bessel
    0.82
     stockfoto
    0.81
    ﻉ
    0.80
     сотрудников
    0.80
     магазине
    0.79
     shumë
    0.78
     superoxide
    0.77
     pavil
    0.77
    POSITIVE LOGITS
    이지
    0.79
    م
    0.78
    дне
    0.72
    }.",
    0.72
    ク
    0.70
    м
    0.69
     discipline
    0.68
    서는
    0.67
    서를
    0.67
    m
    0.67
    Activations Density 0.000%

    No Known Activations