© 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. 39645
    Prev
    Next
    INDEX
    Explanations

    South Dakota partnership

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

    The neuron strongly fires on individual numeric‐digit tokens (and similar single–character number/hex tokens).

    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
    ฌ
    -1.20
    8
    -1.17
    9
    -1.08
    0
    -1.04
    3
    -1.04
    5
    -1.03
    4
    -1.03
     jurk
    -1.01
    2
    -1.00
    zené
    -0.95
    POSITIVE LOGITS
     Asegúrese
    1.09
     Aseg
    1.06
    )،
    1.05
     contratto
    1.05
     virtudes
    1.02
     Алексей
    1.00
     Lleva
    1.00
     biela
    0.98
     konkuren
    0.97
    Portale
    0.95
    Activations Density 0.112%

    No Known Activations