© 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. 1855
    Prev
    Next
    INDEX
    Explanations

    purpose is to describe you

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

    This neuron detects numeric measurements and dimensions (numbers paired with units).

    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
    我对
    0.78
     Öffentlichkeit
    0.76
     trebalo
    0.75
     EditText
    0.75
    我覺得
    0.75
     treba
    0.74
     쓸
    0.73
    れた
    0.72
    有所
    0.72
     chciał
    0.72
    POSITIVE LOGITS
     ourselves
    1.08
    our
    0.96
     nossos
    0.96
     vårt
    0.96
     sommes
    0.94
     nossa
    0.93
     nostro
    0.92
     our
    0.89
     nostri
    0.89
     nosso
    0.88
    Activations Density 0.572%

    No Known Activations