© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6526
    Prev
    Next
    INDEX
    Explanations

    specifications and keywords

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

    The neuron is highly activated by very common, high‐frequency tokens (common words and function words).

    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
    ありがとう
    0.82
     ampia
    0.81
     віднов
    0.80
    ôtels
    0.80
     progett
    0.79
    大幅
    0.77
    옛
    0.77
    𝗸
    0.76
     найкра
    0.76
    𝗠
    0.74
    POSITIVE LOGITS
     sweating
    0.73
     Dö
    0.73
    dje
    0.69
    ej
    0.68
    steacher
    0.68
     adults
    0.66
    lm
    0.65
     (£
    0.65
     beraten
    0.64
    ló
    0.64
    Activations Density 0.000%

    No Known Activations