© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 84681
    Prev
    Next
    INDEX
    Explanations

    casting spells or actions

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

    The neuron consistently lights up on standalone numeric tokens (e.g., page numbers, damage values, counts), i.e. it detects numbers in the text.

    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
    urface
    -1.08
    (&
    -0.99
    zzet
    -0.98
     quarantined
    -0.96
    ου
    -0.96
    趿
    -0.96
     atyp
    -0.95
     KIL
    -0.94
     EVEN
    -0.93
     QUALITY
    -0.93
    POSITIVE LOGITS
     invigor
    1.12
     impending
    1.09
     although
    1.08
     cautious
    1.00
     both
    0.99
     increased
    0.95
     enhanced
    0.94
     wildly
    0.93
     Although
    0.91
     giving
    0.91
    Activations Density 0.022%

    No Known Activations