© 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. 112759
    Prev
    Next
    INDEX
    Explanations

    smooth or seamless transitions

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

    The neuron identifies occurrences of “smooth” (and its variants like “smoothly”) indicating a seamless or fluid process.

    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
     is
    -1.42
     more
    -1.27
     günstiger
    -1.24
     aptly
    -1.23
     for
    -1.23
    bigliamento
    -1.21
     now
    -1.20
     in
    -1.20
     adjoining
    -1.20
     خونه
    -1.18
    POSITIVE LOGITS
    ⁼
    1.50
    》《
    1.41
    哪儿
    1.28
    WithIdentifier
    1.27
    {}{}
    1.27
    俦
    1.23
    蹀
    1.18
    }
    1.16
     grâce
    1.16
    This
    1.16
    Activations Density 0.024%

    No Known Activations