© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 104321
    Prev
    Next
    INDEX
    Explanations

    locking and unlocking mechanisms

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

    the verb "lock" and related locking/unlocking actions, particularly in contexts involving doors, mechanisms, or security systems.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron detects mentions of mechanical locking devices or actions (e.g., locking, locked, latch, unlock) in the text.

    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
    ilets
    -1.66
     Singapur
    -1.64
    takings
    -1.48
    热血
    -1.48
    </caption>
    -1.47
    ativement
    -1.45
    💡
    -1.45
    nement
    -1.45
    鐽
    -1.45
    pography
    -1.42
    POSITIVE LOGITS
     our
    1.87
     posiada
    1.52
     wskaz
    1.49
    }$
    1.49
     mengubah
    1.46
     erstes
    1.46
     čet
    1.44
    3
    1.41
     thier
    1.38
     gewinnt
    1.38
    Activations Density 0.015%

    No Known Activations