© 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. 11445
    Prev
    Next
    INDEX
    Explanations

    slippery, slick, or bumpy surfaces

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

    The neuron fires strongly on the adjective “slippery,” whether describing physical surfaces (e.g. slippery floor) or metaphorical slippery slopes.

    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
    o
    -2.80
    '
    -2.77
     '
    -2.70
    1
    -2.59
    )
    -2.56
    L
    -2.47
    </em>
    -2.47
    s
    -2.44
     they
    -2.33
    In
    -2.31
    POSITIVE LOGITS
    狆
    3.11
    ஂ
    2.70
    驁
    2.64
    鋮
    2.50
    轫
    2.48
     slippery
    2.42
    龃
    2.38
    谵
    2.36
     simplistic
    2.33
     яка
    2.30
    Activations Density 0.002%

    No Known Activations