© 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. 9739
    Prev
    Next
    INDEX
    Explanations

    continue dancing

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

    The neuron is a specialist detector for floating‐point numbers.

    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
    redir
    0.82
     contenir
    0.77
     mulut
    0.75
    ре
    0.74
    количество
    0.73
     thisobject
    0.71
     unhappiness
    0.71
    宾
    0.70
    比赛
    0.70
    ıma
    0.70
    POSITIVE LOGITS
    CE
    0.86
    ME
    0.80
    ている
    0.80
     ETFs
    0.77
    MEGA
    0.75
    FT
    0.74
    ul
    0.74
    OS
    0.74
    CJK
    0.74
    r
    0.73
    Activations Density 0.000%

    No Known Activations