© 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. 13220
    Prev
    Next
    INDEX
    Explanations

    place names and specific keywords

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

    The neuron highlights infrequent, content-bearing words (i.e. relatively rare or domain-specific nouns and adjectives).

    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
    啈
    0.99
    是用
    0.87
    挀
    0.84
    作战
    0.79
    嶈
    0.77
    俺
    0.77
    兟
    0.76
    𝚅
    0.75
    觟
    0.75
     Vulcan
    0.74
    POSITIVE LOGITS
    ishi
    0.88
    íl
    0.81
    ied
    0.79
     noticeable
    0.79
     примерно
    0.77
    atz
    0.76
    etry
    0.76
    ips
    0.75
     inflows
    0.75
    3
    0.75
    Activations Density 0.000%

    No Known Activations