© 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. 14010
    Prev
    Next
    INDEX
    Explanations

    code syntax, programming, natural language

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

    The neuron predominantly activates on numeric tokens (e.g. version or index numbers, numeric literals, and 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
    يال
    -0.91
     løpet
    -0.90
     verticales
    -0.88
     Nature
    -0.85
    МЫ
    -0.85
     nature
    -0.85
    воло
    -0.84
    جري
    -0.84
     förra
    -0.84
    𝟎
    -0.84
    POSITIVE LOGITS
    Mustard
    0.94
    然的
    0.89
    皑
    0.82
    معرفی
    0.81
    Jojo
    0.81
    Nossa
    0.79
    Mermaid
    0.79
    沒想到
    0.79
    Ghosts
    0.78
    Hiking
    0.78
    Activations Density 0.004%

    No Known Activations