© 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. 24-GEMMASCOPE-2-RES-16K
    7. 4178
    Prev
    Next
    INDEX
    Explanations

    list items

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

    The neuron fires on words expressing simplicity or ease (e.g. “easy”).

    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
     braced
    0.77
    brace
    0.74
    вой
    0.73
    alling
    0.69
    श्रेष्ठ
    0.69
    co
    0.67
     получается
    0.66
    𝘺
    0.65
    マスター
    0.65
    y
    0.65
    POSITIVE LOGITS
     errori
    0.82
     plupart
    0.81
    蒇
    0.79
    bedarf
    0.77
     kurulum
    0.77
     ISNI
    0.77
     peinture
    0.76
     výro
    0.76
     diffusivity
    0.75
     Raton
    0.75
    Activations Density 0.001%

    No Known Activations