© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7482
    Prev
    Next
    INDEX
    Explanations

    animals in water

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

    The neuron responds strongly to less common, content‐rich words—especially technical, domain-specific, or otherwise “rare” terms.

    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_31_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
     magasins
    0.58
     empresario
    0.55
     doğum
    0.52
     seams
    0.51
     quartiers
    0.50
    อะคาเดมี
    0.50
     آبادی
    0.50
    篙
    0.50
     자료
    0.50
     sculpted
    0.50
    POSITIVE LOGITS
     animals
    2.50
    animals
    2.31
     Animals
    2.16
     birds
    2.11
    Animals
    2.11
     mammals
    2.06
     animais
    2.05
     squirrels
    2.00
     animali
    2.00
     animales
    1.99
    Activations Density 0.926%

    No Known Activations