© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 2656
    Prev
    Next
    INDEX
    Explanations

    company names ending in Inc. or LLC

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

    The neuron strongly activates on corporate and organizational names (e.g. tokens like “Inc.”, “Jr.”, “com”), i.e. it detects mentions of formal entities.

    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
    ム
    0.73
    های
    0.68
    까지
    0.68
    𝙄
    0.65
    นี
    0.64
    σιμο
    0.62
    läge
    0.61
    ོན་
    0.61
    -...
    0.59
    יים
    0.58
    POSITIVE LOGITS
    .,
    0.99
     estrateg
    0.70
    acher
    0.66
    .),
    0.65
    asco
    0.64
    .;
    0.62
     investimentos
    0.62
     என்பவர்
    0.61
     (“
    0.60
    }$.,
    0.60
    Activations Density 0.029%

    No Known Activations