© 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. 129623
    Prev
    Next
    INDEX
    Explanations

    The neuron selectively activates on standalone numeric tokens (digits).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    Control of effects

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     compartió
    -1.10
    みなさん
    -1.10
     gastar
    -1.03
     garantit
    -1.02
     võib
    -1.02
    openqa
    -1.00
    },
    -0.99
    ६
    -0.98
    Související
    -0.98
    RotationOrder
    -0.98
    POSITIVE LOGITS
    partements
    1.13
     respectively
    1.05
     which
    1.00
     since
    1.00
     because
    0.99
    采用
    0.96
     as
    0.93
    𝑂
    0.91
    这两个
    0.90
    ete
    0.88
    Activations Density 0.000%

    No Known Activations