© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 511
    Prev
    Next
    INDEX
    Explanations

    that introducing clauses

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

    The neuron strongly activates on numeric tokens—especially floating‐point numbers with decimal points.

    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
    ()
    0.28
    .
    0.28
    }
    0.26
     a
    0.26
     the
    0.25
    _
    0.25
    )
    0.24
    ?
    0.24
    },
    0.24
    ).
    0.23
    POSITIVE LOGITS
     außergewöhn
    0.23
    មិន
    0.23
    ផ្តល់
    0.22
     يساعد
    0.22
    रिडोर
    0.22
     بدور
    0.22
     ໜອງ
    0.22
    គ្មាន
    0.22
     উৎকৃষ্ট
    0.21
    ጨም
    0.21
    Activations Density 0.948%

    No Known Activations