© 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. 4943
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly fires on occurrences of the verb “want” (including forms like “want” and “wanted”).

    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
    ために
    1.12
     cinerea
    1.12
    磧
    1.09
    恃
    1.09
    ত্বের
    1.07
    cline
    1.05
    েকের
    1.02
    Ꭸ
    1.02
    എം
    1.00
     ஆன
    1.00
    POSITIVE LOGITS
    et
    1.31
    اد
    1.24
    ا
    1.16
    र्गत
    1.16
    ă
    1.13
    t
    1.10
    ל
    1.10
    ת
    1.09
    ت
    1.07
    तः
    1.05
    Activations Density 0.083%

    No Known Activations