© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93119
    Prev
    Next
    INDEX
    Explanations

    volume or vol

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

    The neuron is specialized to detect structured academic journal citation metadata such as ISSN numbers, volume/issue labels, and journal abbreviations in parentheses.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    claimer
    -0.76
    InMillis
    -0.75
    umpulkan
    -0.75
     romanzo
    -0.74
    memcmp
    -0.74
    /></
    -0.73
    bürger
    -0.71
    ℛ
    -0.71
     sonra
    -0.71
     בת
    -0.70
    POSITIVE LOGITS
     Volume
    4.28
     Vol
    4.16
     volume
    4.13
    Volume
    3.97
     vol
    3.75
    Vol
    3.55
    volume
    3.39
    vol
    3.19
    VOLUME
    3.09
     volumes
    3.08
    Activations Density 0.095%

    No Known Activations