© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 14191
    Prev
    Next
    INDEX
    Explanations

    zero-tolerance area

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

    The neuron strongly fires on discourse-level transition markers—i.e. words that introduce or shift topics (for example adverbs like “rather” or “last,” section headers like “News,” and pronouns opening a new discussion such as “we”).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    it
    0.93
    L
    0.77
    ﻟ
    0.76
    Diag
    0.74
    itivo
    0.73
    Page
    0.71
    keto
    0.70
     stel
    0.70
    慶
    0.69
    SA
    0.67
    POSITIVE LOGITS
    ató
    0.94
     kilómetros
    0.86
    ára
    0.86
     publicó
    0.84
     ҳа
    0.82
    пы
    0.81
     была
    0.80
     лишь
    0.80
     McCr
    0.79
     препят
    0.79
    Activations Density 0.000%

    No Known Activations