© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 6697
    Prev
    Next
    INDEX
    Explanations

    a specific value or statement

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

    The neuron fires on mentions of dumpsters or large waste‐container/rental services.

    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
    ⁇
    0.64
    పో
    0.62
     biologie
    0.62
    טי
    0.61
    Οι
    0.61
     Gölü
    0.61
    𝓂
    0.59
    래
    0.59
    "!
    0.58
    bacteria
    0.58
    POSITIVE LOGITS
     yaitu
    0.66
     sebagaimana
    0.64
     Called
    0.64
     punya
    0.62
    Cipher
    0.62
     Mullins
    0.61
    unitas
    0.61
    简称
    0.60
     Verw
    0.60
     Corm
    0.60
    Activations Density 0.000%

    No Known Activations