© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 64616
    Prev
    Next
    INDEX
    Explanations

    journal abbreviations

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

    The neuron activates on tokens that are parts of academic journal citations (e.g. journal‐name abbreviations and volume numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     or
    -1.60
     on
    -1.41
    With
    -1.27
     dengan
    -1.21
     untuk
    -1.19
     with
    -1.19
     sekarang
    -1.17
     für
    -1.16
     now
    -1.13
     and
    -1.12
    POSITIVE LOGITS
    erobic
    1.49
     acclaimed
    1.29
    <bos>
    1.21
    ఱ
    1.17
     weichen
    1.17
    cestor
    1.15
    костюм
    1.14
    maphore
    1.14
    ょ
    1.14
    があり
    1.13
    Activations Density 0.002%

    No Known Activations