© 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-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 67959
    Prev
    Next
    INDEX
    Explanations

    comment lines

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

    The neuron fires on standalone numeric tokens (e.g. line numbers or similar numeric literals).

    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
     for
    -1.41
     of
    -1.34
     on
    -1.22
     both
    -1.20
     Kommune
    -1.17
    werf
    -1.16
    کتری
    -1.06
     reise
    -1.05
     Etik
    -1.05
     breed
    -1.05
    POSITIVE LOGITS
    どうやって
    1.38
     accesorio
    1.22
     mejoras
    1.20
    今度
    1.20
     brimming
    1.16
    ཾ
    1.16
     sebagainya
    1.16
    雰囲
    1.15
     verdaderos
    1.15
    认真的
    1.13
    Activations Density 0.007%

    No Known Activations