© 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. 1994
    Prev
    Next
    INDEX
    Explanations

    colonia lunar, staff, plataforma, módulo

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

    The neuron fires on non-English proper names and key foreign-language tokens (e.g. French or Spanish place/institution/event names).

    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
     કરવી
    0.75
    iguing
    0.68
    许多
    0.66
     一个
    0.66
    ShaderType
    0.66
    他们
    0.65
    鄔
    0.64
    店铺
    0.64
    差距
    0.63
     问题
    0.63
    POSITIVE LOGITS
     de
    1.34
     universitaria
    1.23
     educativa
    1.21
     integrada
    1.21
     dirigida
    1.20
     deportiva
    1.19
     italiana
    1.17
     composta
    1.16
     inglesa
    1.16
     dedicada
    1.15
    Activations Density 0.083%

    No Known Activations