© 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. 3922
    Prev
    Next
    INDEX
    Explanations

    cheap in negotiating

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

    The neuron primarily activates on numeric tokens, i.e. numbers and measurement expressions.

    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
    各类
    1.12
    各種
    0.96
    𝘩
    0.95
    bookmarks
    0.93
    𝗴
    0.92
    busca
    0.88
    多
    0.87
    飞行
    0.86
    畄
    0.86
    mimeTypes
    0.85
    POSITIVE LOGITS
     promulg
    0.98
     hindrance
    0.95
     discrimination
    0.94
     grievance
    0.94
     applicability
    0.91
     loophole
    0.90
     feces
    0.90
     decency
    0.89
     credence
    0.87
     willingness
    0.86
    Activations Density 4.371%

    No Known Activations