© 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. 31-GEMMASCOPE-2-RES-16K
    7. 9229
    Prev
    Next
    INDEX
    Explanations

    Kindle and tablet devices

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

    The main thing this neuron does is detect mentions of digital book formats and online download or reading 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_31_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
    omey
    0.69
    addSub
    0.64
    ボ
    0.63
    пы
    0.61
    aksan
    0.58
    নায়
    0.57
     ウォ
    0.57
    экс
    0.55
    мою
    0.55
    풉
    0.55
    POSITIVE LOGITS
     College
    0.64
     lecteurs
    0.64
     otp
    0.63
     Scop
    0.61
    <h4>
    0.59
    晚上
    0.59
     Reader
    0.57
     FontWeight
    0.57
     вечер
    0.57
    <h2>
    0.57
    Activations Density 0.006%

    No Known Activations