© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9502
    Prev
    Next
    INDEX
    Explanations

    Give them

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

    This neuron strongly activates on capitalized names and technical nouns (proper nouns and branded/product terms).

    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
    izarra
    0.71
    ívar
    0.67
    agog
    0.66
    
    0.66
    Aile
    0.64
    Funcion
    0.64
    ﻨ
    0.64
    漃
    0.64
    Política
    0.63
    retrato
    0.63
    POSITIVE LOGITS
     the
    0.73
     wanted
    0.63
    .
    0.61
     a
    0.58
     "
    0.57
     The
    0.55
     study
    0.54
     andre
    0.54
    the
    0.53
     picture
    0.53
    Activations Density 0.253%

    No Known Activations