© 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
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 10692
    Prev
    Next
    INDEX
    Explanations

    Boil, booleans, float, boys

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

    This neuron responds strongly to tokens beginning with the letter sequence “Bo,” effectively detecting words that start with “Bo.”

    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
     ionization
    0.55
     lắm
    0.55
     utmost
    0.55
     flavored
    0.54
     بت
    0.54
    !\!\
    0.54
     часто
    0.54
     请
    0.54
     ライト
    0.53
     flapping
    0.53
    POSITIVE LOGITS
    Bo
    1.17
     Bo
    1.06
     BO
    0.93
    Бо
    0.87
     Бо
    0.85
    Boo
    0.82
     bo
    0.80
    Boost
    0.76
    bo
    0.75
    BO
    0.74
    Activations Density 0.171%

    No Known Activations