© 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. 101208
    Prev
    Next
    INDEX
    Explanations

    dialogue contents

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

    The neuron fires on relatively long, content-bearing subword fragments (e.g. uncommon technical terms or proper-name pieces) rather than on short or high-frequency tokens.

    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
    It
    -2.72
    If
    -2.67
    They
    -2.66
    </sup>
    -2.59
    謦
    -2.52
    We
    -2.50
     taką
    -2.48
    躝
    -2.48
    ).”
    -2.47
    ᠂
    -2.47
    POSITIVE LOGITS
    􀂃
    2.83
     ‘‘
    2.69
     ‘
    2.69
    蚨
    2.67
     BOTH
    2.55
     ทั้ง
    2.41
    嘏
    2.41
     freakin
    2.39
    皷
    2.39
    燄
    2.36
    Activations Density 0.007%

    No Known Activations