© 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. 12080
    Prev
    Next
    INDEX
    Explanations

    business to business

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

    The neuron strongly lights up on very common high‐frequency words (especially function words like “for,” “by,” “after,” “and,” etc.) and so seems to be detecting common English tokens.

    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
    𒉺
    0.55
    
    0.54
    घात
    0.53
     ϒ
    0.50
     সুরক্ষা
    0.50
    ᵁ
    0.50
     Öl
    0.49
    
    0.49
    मेस्टर
    0.49
    闯
    0.48
    POSITIVE LOGITS
    々
    1.45
    々の
    1.37
    々に
    1.34
    々は
    1.14
    ๆ
    0.98
    ໆ
    0.96
    々と
    0.96
    々な
    0.94
    ៗ
    0.93
     ๆ
    0.86
    Activations Density 0.917%

    No Known Activations