© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 11941
    Prev
    Next
    INDEX
    Explanations

    news list items, numbers, or code blocks

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

    The neuron spikes on relatively uncommon, information‐heavy tokens (i.e. rare or content-rich 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
    t
    0.83
    tol
    0.71
     فری
    0.69
    til
    0.68
    ależy
    0.68
    сль
    0.68
    mä
    0.67
    take
    0.65
    是因为
    0.65
    tat
    0.64
    POSITIVE LOGITS
     demeanor
    0.80
     strides
    0.78
     disgraced
    0.77
    
    0.77
     shortstop
    0.76
     sulfide
    0.75
     reigns
    0.74
     malfunctions
    0.74
     PERIOD
    0.73
    toUpperCase
    0.71
    Activations Density 0.000%

    No Known Activations