© 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. 9243
    Prev
    Next
    INDEX
    Explanations

    turbulent, entangled, repugnant

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

    The neuron responds most strongly to tokens that are English adjectives or past-participles ending in “-ed” or “-ent” (e.g. entangled, turbulent, repugnant).

    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
    壜
    -2.88
     kupa
    -2.63
     کیا
    -2.53
    ются
    -2.53
    跸
    -2.52
     rajut
    -2.50
    臵
    -2.42
     绒
    -2.41
    鏐
    -2.39
    廛
    -2.36
    POSITIVE LOGITS
    ]
    3.08
    <em>
    2.75
    」
    2.72
     has
    2.59
    w
    2.55
    筱
    2.50
    d
    2.47
    }
    2.45
     we
    2.44
     seem
    2.42
    Activations Density 0.002%

    No Known Activations