© 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. 22-GEMMASCOPE-RES-131K
    7. 35996
    Prev
    Next
    INDEX
    Explanations

    predicting job statistics

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

    This neuron activates on multi-digit numeric tokens (e.g. counts or percentages).

    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
    駸
    -1.36
     plafon
    -1.20
     his
    -1.19
    賸
    -1.16
    檍
    -1.15
     already
    -1.13
     its
    -1.08
    ächst
    -1.06
    ledes
    -1.05
    יבות
    -1.04
    POSITIVE LOGITS
     M
    0.99
    there
    0.93
     junge
    0.93
     F
    0.92
     N
    0.91
     A
    0.89
     in
    0.88
     adjusted
    0.86
     D
    0.85
     How
    0.85
    Activations Density 0.000%

    No Known Activations