© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 6396
    Prev
    Next
    INDEX
    Explanations

    device augmentation goal rating guidance

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

    The neuron strongly activates on the punctuation marks (slashes and periods) used in structured numeric formats such as dates, timestamps, and citation references.

    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
    lı
    0.93
    ak
    0.91
    Duplicate
    0.83
    BU
    0.82
    Nombre
    0.81
    Con
    0.80
    Ad
    0.80
    u
    0.79
    Sim
    0.79
    en
    0.78
    POSITIVE LOGITS
     proffered
    0.96
     subsequ
    0.89
     heyday
    0.89
     stake
    0.87
     narrated
    0.87
     prokary
    0.86
     readout
    0.85
     bookcase
    0.84
     caregiver
    0.83
     cask
    0.82
    Activations Density 0.001%

    No Known Activations