© 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. 11108
    Prev
    Next
    INDEX
    Explanations

    transcriptomic

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

    The neuron is activated by the digit "2" in numbers or dates.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    Čo
    -1.28
    orul
    -1.23
    rierten
    -1.21
    Počet
    -1.13
     золота
    -1.13
     cible
    -1.13
    PRWEB
    -1.13
    ventajas
    -1.10
     sampah
    -1.09
     desmotiv
    -1.09
    POSITIVE LOGITS
     property
    1.26
    天氣
    1.20
     liegenden
    1.20
    的行为
    1.10
     águas
    1.08
    的长
    1.06
     правительства
    1.05
     originalmente
    1.04
     ownership
    1.02
     dived
    1.02
    Activations Density 0.000%

    No Known Activations