© 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. 22-GEMMASCOPE-RES-131K
    7. 72626
    Prev
    Next
    INDEX
    Explanations

    awards and galleries

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

    The neuron flags numeric tokens or numerical expressions (e.g. counts, years, award 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
     that
    -1.89
     didn
    -1.27
     might
    -1.27
     who
    -1.26
     obviously
    -1.22
    !
    -1.14
     then
    -1.13
     wouldn
    -1.11
     already
    -1.11
     could
    -1.11
    POSITIVE LOGITS
     และ
    1.36
     florales
    1.26
    others
    1.22
    mengen
    1.17
     sirena
    1.16
    ㌧
    1.16
    twice
    1.13
    Также
    1.12
     oraz
    1.12
    Sekarang
    1.11
    Activations Density 0.043%

    No Known Activations