© 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. 34-GEMMASCOPE-RES-131K
    7. 83772
    Prev
    Next
    INDEX
    Explanations

    numbers following "Pre"

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

    The neuron activates on numeric tokens (multi­digit numbers, like version numbers or other 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_34/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
    átu
    -1.19
    PhysRev
    -1.08
    }}_
    -1.06
    клопе
    -1.05
    TokenNameDOT
    -1.05
    GeneratedCode
    -1.03
    CommonModule
    -1.01
    rido
    -1.01
    见了
    -1.00
    抑制
    -0.97
    POSITIVE LOGITS
    6
    1.12
    7
    1.08
    3
    1.02
    8
    1.00
    5
    1.00
    4
    0.93
    這個
    0.93
    それにしても
    0.92
    posting
    0.91
     Jungkook
    0.91
    Activations Density 0.001%

    No Known Activations