© 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. 9062
    Prev
    Next
    INDEX
    Explanations

    // or code comments

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

    The neuron flags uncommon or named‐entity tokens—especially proper names and places.

    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
    이션
    0.86
    但这
    0.84
     headlined
    0.82
    Გ
    0.80
    ার্
    0.79
    შე
    0.79
    コリ
    0.79
    یہ
    0.77
    éor
    0.76
    올
    0.76
    POSITIVE LOGITS
     Kanton
    0.96
     Norden
    0.82
     bakan
    0.81
    methoxy
    0.79
     meeste
    0.79
    butyl
    0.77
    :]
    0.77
     Nacht
    0.77
    pyridin
    0.76
     batik
    0.76
    Activations Density 0.001%

    No Known Activations