© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 4963
    Prev
    Next
    INDEX
    Explanations

    respect and acknowledgement

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on the lemma “celebrate” (e.g. celebrating, celebrated, celebration, celebrates).

    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
    е
    1.05
    นะคะ
    0.93
    ierzchn
    0.89
     tâche
    0.89
     интересу
    0.89
     émotion
    0.88
    }}_{\
    0.86
     penilaian
    0.85
    敎
    0.85
     définie
    0.84
    POSITIVE LOGITS
     commemorating
    1.11
     birthdays
    1.09
     anivers
    1.01
     victories
    1.00
     accomplishments
    0.96
     togetherness
    0.96
     Achievements
    0.95
     deserving
    0.95
     milestones
    0.95
     mừng
    0.95
    Activations Density 0.114%

    No Known Activations