© 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. 9218
    Prev
    Next
    INDEX
    Explanations

    keep yoursite allowstransition from

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

    The neuron flags formally introduced or defined domain‐specific terms (e.g. headings or labels in legal, mathematical, or technical definitions).

    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
    0.81
        
    0.75
    {:
    0.72
    By
    0.69
    to
    0.66
    emente
    0.66
    City
    0.66
    Sci
    0.65
    =
    0.64
    U
    0.64
    POSITIVE LOGITS
     Artin
    1.17
     Drinfeld
    1.01
     Kano
    1.00
     Vitor
    0.99
     Vitória
    0.98
     mannit
    0.98
     Grassmann
    0.97
     اﻻ
    0.97
     Kähler
    0.95
     Huyền
    0.93
    Activations Density 0.000%

    No Known Activations