© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 12813
    Prev
    Next
    INDEX
    Explanations

    continue reading

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

    This neuron fires on “Continue” prompts (e.g. navigation or “Continue reading” links).

    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
     учетом
    -2.61
    葙
    -2.42
    }$
    -2.38
            
    -2.25
    秾
    -2.20
    嚒
    -2.17
    ೣ
    -2.17
     besoin
    -2.16
    ⧠
    -2.16
    葑
    -2.08
    POSITIVE LOGITS
    ↵
    2.86
    刧
    2.25
    ねー
    2.23
     schien
    2.11
    幾天
    2.11
    があるので
    2.08
    寶寶
    2.06
    緜
    2.05
    睒
    2.05
    クソ
    2.00
    Activations Density 0.006%

    No Known Activations