© 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. 9560
    Prev
    Next
    INDEX
    Explanations

    following "love"

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

    The neuron identifies unusually rare or complex vocabulary tokens (i.e. low-frequency, “fancy” words).

    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
    朗普
    0.82
    启动
    0.77
    竣
    0.77
    انون
    0.74
    足球
    0.74
    珬
    0.74
    浧
    0.74
    ㈡
    0.73
    缓慢
    0.71
    ौनक
    0.71
    POSITIVE LOGITS
    ,
    0.93
     pairings
    0.90
    aciones
    0.82
    plas
    0.77
     bags
    0.77
     Vamp
    0.77
    he
    0.76
     implements
    0.75
     cher
    0.75
    edom
    0.74
    Activations Density 0.001%

    No Known Activations