© 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. 7062
    Prev
    Next
    INDEX
    Explanations

    geographic hierarchy

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

    The neuron fires on the backslash separators used to delimit category hierarchies (e.g. the “\” between category levels).

    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
     &/
    0.76
     rDNA
    0.69
     glTexCoord
    0.68
    
    0.67
    此类
    0.66
     madad
    0.66
    쿄
    0.65
    rischen
    0.64
    埇
    0.64
     diret
    0.63
    POSITIVE LOGITS
    画家
    0.73
    eres
    0.73
    アメリカ
    0.72
     painters
    0.71
     philosophers
    0.70
    oir
    0.69
    ości
    0.68
    Artists
    0.68
     artists
    0.68
    If
    0.68
    Activations Density 0.000%

    No Known Activations