© 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. 5542
    Prev
    Next
    INDEX
    Explanations

    type of

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

    This neuron never fires—its activations stay at zero and it does not detect any pattern.

    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
    up
    0.89
     a
    0.88
    w
    0.83
     an
    0.81
    ER
    0.79
    ag
    0.76
     Twenty
    0.75
     the
    0.73
    THON
    0.72
    ERE
    0.71
    POSITIVE LOGITS
     kelamin
    1.37
    类型的
    1.02
    类型
    1.01
     类型
    0.99
     종류
    0.98
     típus
    0.96
     유형
    0.93
     устройств
    0.93
     informacija
    0.88
    𒐪
    0.88
    Activations Density 0.040%

    No Known Activations