© 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. 92484
    Prev
    Next
    INDEX
    Explanations

    quotes ending sentences

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

    The neuron strongly activates on numeric tokens (sequences of digits).

    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
    ﻧ
    -1.05
     raconte
    -1.02
     gmina
    -1.00
     hectáreas
    -0.98
    AuthGuard
    -0.97
    รวจ
    -0.92
    приклад
    -0.91
    っております
    -0.91
     например
    -0.91
     >
    -0.90
    POSITIVE LOGITS
     this
    2.00
     later
    1.88
    这句话
    1.67
    Later
    1.65
     Later
    1.49
     truer
    1.49
     Translation
    1.46
     Sounds
    1.45
    Translation
    1.40
     implying
    1.40
    Activations Density 0.047%

    No Known Activations