© 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. 84032
    Prev
    Next
    INDEX
    Explanations

    self-control and impulse control

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

    The neuron fires on words and phrases that express self‐control or restraint (e.g., restrain, control, stop oneself).

    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
    '
    -2.05
    v
    -1.59
     Studying
    -1.36
    *
    -1.33
    着一个
    -1.33
     atlik
    -1.31
    甞
    -1.30
     prouver
    -1.26
    ve
    -1.26
     dabar
    -1.25
    POSITIVE LOGITS
    ;
    1.70
     inappropri
    1.45
    новништво
    1.44
    TextHelper
    1.43
    琹
    1.38
     adresu
    1.36
    日まで
    1.36
    ），
    1.34
    )：
    1.33
    ։
    1.33
    Activations Density 0.024%

    No Known Activations