© 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. 10-GEMMASCOPE-RES-131K
    7. 80773
    Prev
    Next
    INDEX
    Explanations

    staging and follow-up

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

    The neuron chiefly detects occurrences of the words “stage” or “staging” in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    3
    -2.44
    注意事
    -2.39
    7
    -2.36
    5
    -2.17
    2
    -2.14
    ly
    -2.08
    en
    -2.06
     messa
    -2.02
     venuto
    -1.97
     toscana
    -1.95
    POSITIVE LOGITS
    父の
    2.42
    皷
    2.22
    荸
    2.19
     manter
    2.14
    ぜひ
    2.13
    莛
    2.13
    presumably
    2.05
    縞
    2.05
     dê
    2.05
    actéristiques
    2.05
    Activations Density 0.004%

    No Known Activations