© 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. 9875
    Prev
    Next
    INDEX
    Explanations

    building or to build

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

    The neuron is basically a “position” detector—it fires strongly for tokens appearing far along (later) in each input sequence.

    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
    s
    0.84
    egin
    0.80
    doc
    0.78
    rule
    0.78
     Determines
    0.77
    tal
    0.76
    reviews
    0.76
    tests
    0.75
    Determ
    0.75
    two
    0.73
    POSITIVE LOGITS
     contrasting
    0.88
     bodyguard
    0.84
     szín
    0.82
     speedometer
    0.80
     euthanasia
    0.80
    䀓
    0.79
    জাহ
    0.79
     majesty
    0.78
     reação
    0.78
     semakin
    0.77
    Activations Density 0.001%

    No Known Activations