© 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. 13471
    Prev
    Next
    INDEX
    Explanations

    file scope declaration

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

    This neuron fires strongly on uncommon or low-frequency content words (i.e. rare tokens) in the text.

    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
    ምን
    1.00
    ТУ
    0.96
    StoredKeys
    0.95
     gewoon
    0.94
    DeviceCompliance
    0.93
    меется
    0.93
    𝗢
    0.92
    𝗮
    0.91
    ኺ
    0.91
    рифмети
    0.91
    POSITIVE LOGITS
    r
    0.89
    f
    0.87
    la
    0.84
    az
    0.83
    id
    0.83
    ct
    0.82
    us
    0.81
    as
    0.77
    og
    0.77
    ub
    0.76
    Activations Density 0.000%

    No Known Activations