© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 14262
    Prev
    Next
    INDEX
    Explanations

    grade fixed income

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

    The neuron strongly activates on words that are exactly seven letters long.

    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
     प्रसार
    0.96
     promover
    0.94
    которы
    0.94
     pasando
    0.93
     colocando
    0.91
    ﺭ
    0.91
    FBSDKInternal
    0.89
    ujjati
    0.87
     Германии
    0.85
    ремя
    0.84
    POSITIVE LOGITS
    o
    0.71
     to
    0.68
    ル
    0.66
    ç
    0.66
    ét
    0.65
    від
    0.65
     follower
    0.65
    -
    0.65
     started
    0.65
     P
    0.64
    Activations Density 0.000%

    No Known Activations