© 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. 24-GEMMASCOPE-2-RES-16K
    7. 9901
    Prev
    Next
    INDEX
    Explanations

    offers, lobes, shellcode

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

    The neuron detects mentions of concrete items or supplies that a procedure calls for—things like ingredients (salt, pepper), cookware or tools (glasses, shades), and other objects you need to add, bring, or use.

    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
     financiación
    0.82
    全ての
    0.80
     addirittura
    0.80
     guerras
    0.79
     efectivamente
    0.79
    ༼
    0.77
     insanely
    0.77
    既に
    0.77
     nuovamente
    0.77
     financement
    0.76
    POSITIVE LOGITS
     for
    0.74
     No
    0.72
     modeling
    0.70
     features
    0.68
     modestly
    0.67
     A
    0.67
     modest
    0.67
     selections
    0.65
     at
    0.65
     format
    0.65
    Activations Density 0.010%

    No Known Activations