© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27163
    Prev
    Next
    INDEX
    Explanations

    moksha language

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

    This neuron responds to standalone numeric tokens (digit sequences).

    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
     profesora
    -1.12
     erstaun
    -1.05
     latter
    -1.05
     Tienen
    -1.04
    inerja
    -0.98
     libere
    -0.97
     Pandemie
    -0.97
    ￦
    -0.96
    Мне
    -0.94
     ſa
    -0.94
    POSITIVE LOGITS
     if
    0.98
     it
    0.98
    жать
    0.92
     or
    0.90
    ۃ
    0.88
     there
    0.86
     of
    0.84
     no
    0.82
     at
    0.82
     and
    0.82
    Activations Density 0.002%

    No Known Activations