© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113167
    Prev
    Next
    INDEX
    Explanations

    winch, inch, davits, lowered, hangar

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

    The neuron strongly activates on mentions of "winch" (and related hoisting or pulling devices).

    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
    翾
    -1.99
    ...”
    -1.98
    袮
    -1.88
    !”,
    -1.84
    ػ
    -1.80
    瑧
    -1.75
    唞
    -1.75
     休閒
    -1.72
     Años
    -1.72
    紕
    -1.71
    POSITIVE LOGITS
    y
    3.05
    \
    2.50
     "
    2.38
    8
    2.19
    </i>
    2.08
    OS
    1.95
    </h1>
    1.93
     WITH
    1.83
     You
    1.79
     u
    1.77
    Activations Density 0.005%

    No Known Activations