© 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. 31-GEMMASCOPE-2-RES-16K
    7. 8655
    Prev
    Next
    INDEX
    Explanations

    build a

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

    The neuron activates on numerical expressions (digits and quantities) in the text.

    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
     рей
    0.59
    mathspace
    0.53
    🧛
    0.53
     অত্যাচারের
    0.53
     invasions
    0.52
    ائح
    0.51
     ঘোর
    0.50
     گردش
    0.50
    旪
    0.50
    🌘
    0.50
    POSITIVE LOGITS
     explosives
    2.63
     explosive
    2.53
     Explos
    2.50
     deton
    2.47
    爆炸
    2.42
     explosion
    2.30
    explos
    2.30
     explosions
    2.25
     explode
    2.23
     detonation
    2.23
    Activations Density 0.266%

    No Known Activations