© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 85687
    Prev
    Next
    INDEX
    Explanations

    creating or determining actions

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

    The neuron flags key action verbs that express deliberate or goal‐oriented operations (e.g. determine, create, make, keep, see).

    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
     by
    -1.50
    一样
    -1.41
    detek
    -1.34
    herself
    -1.27
    前回の
    -1.27
     and
    -1.23
     تعمل
    -1.22
    
    -1.22
    ଚ
    -1.22
     activiteiten
    -1.20
    POSITIVE LOGITS
    </i>
    1.84
    </u>
    1.66
    </h5>
    1.53
    </b>
    1.52
     They
    1.48
     =
    1.46
    h
    1.38
    0
    1.33
    ↵↵↵↵↵↵
    1.31
     either
    1.31
    Activations Density 0.140%

    No Known Activations