© 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. 74282
    Prev
    Next
    INDEX
    Explanations

    giving in or yielding

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

    The neuron fires on words describing backing down, giving in, or otherwise capitulating (e.g. cave, compromise, surrender, capitulation, yield).

    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
     incluso
    -1.35
    ÁRIO
    -1.26
     arvio
    -1.26
    !!!!!!!!!
    -1.26
    vidéo
    -1.21
    still
    -1.20
    ियां
    -1.19
    !!!!!!!
    -1.19
     jät
    -1.19
    IBILITY
    -1.18
    POSITIVE LOGITS
    もしくは
    1.43
     “
    1.28
     collapsing
    1.25
    艽
    1.21
    fachada
    1.16
    bicicleta
    1.13
     levar
    1.13
     funcion
    1.13
     from
    1.10
    または
    1.10
    Activations Density 0.033%

    No Known Activations