© 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. 15549
    Prev
    Next
    INDEX
    Explanations

    mathematical and technical terms

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

    This neuron does not detect any coherent linguistic or semantic feature—it fires erratically on individual tokens without a consistent pattern.

    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
     d
    0.82
     Unterstützung
    0.82
     Nhưng
    0.77
     giocare
    0.75
     Erinner
    0.75
     Erkennt
    0.75
     Där
    0.71
     proximité
    0.70
     Qxc
    0.70
     Delegates
    0.69
    POSITIVE LOGITS
     hydraz
    0.84
    salon
    0.77
    وای
    0.76
     теркәлүсез
    0.75
    ເສ
    0.74
    湋
    0.74
    зге
    0.73
    PARAM
    0.73
    lccc
    0.73
    dimethyl
    0.72
    Activations Density 0.001%

    No Known Activations