© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 14835
    Prev
    Next
    INDEX
    Explanations

    release, comments, study, GmbH

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

    The neuron spikes on capitalized named entities—especially place and organization names (and associated numeric/address details).

    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
     tzw
    0.70
    ماه
    0.66
    كيف
    0.65
    囘
    0.65
    конец
    0.64
    Foo
    0.63
    mySocket
    0.63
    ZC
    0.62
     tzv
    0.61
    ك
    0.61
    POSITIVE LOGITS
     disappro
    0.68
     getMenuInflater
    0.67
     insists
    0.66
     Appalachian
    0.64
     disapproval
    0.64
     pastors
    0.63
     fpr
    0.62
     encourages
    0.61
     Oklahoma
    0.61
     authorizes
    0.61
    Activations Density 1.200%

    No Known Activations