© 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. 61150
    Prev
    Next
    INDEX
    Explanations

    permanent deal or closingpermanently reduce or closefull time job or fighter

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

    The neuron strongly activates on mentions of “permanent” or “permanently,” especially in phrases about permanent deals or full-time/long-term arrangements.

    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
    AutoModerator
    -1.25
     your
    -1.20
    ႐
    -1.18
    AMPTON
    -1.15
     presentará
    -1.13
    different
    -1.09
    тины
    -1.07
     relatives
    -1.07
    achieved
    -1.07
     extrême
    -1.06
    POSITIVE LOGITS
     instead
    1.40
    
    1.19
     veckan
    1.17
     what
    1.17
    豋
    1.16
     soon
    1.16
     without
    1.15
     it
    1.15
    baomidou
    1.11
    後面
    1.11
    Activations Density 0.087%

    No Known Activations