© 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. 60476
    Prev
    Next
    INDEX
    Explanations

    slack, limp, or drooping

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

    The neuron activates on words that describe drooping or sagging physical states (e.g., sagging, drooping, limp).

    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
     vollständ
    -1.61
     entspre
    -1.55
     individuellen
    -1.54
     solcher
    -1.54
     verwende
    -1.53
    thage
    -1.52
     praktischen
    -1.46
    捶
    -1.45
     besonderer
    -1.45
     размеры
    -1.41
    POSITIVE LOGITS
    ’
    1.65
    佧
    1.46
    ]
    1.44
     sag
    1.43
    ť
    1.39
     annet
    1.38
    the
    1.37
    Ę
    1.30
     Direkt
    1.30
     limp
    1.30
    Activations Density 0.023%

    No Known Activations