© 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. 15110
    Prev
    Next
    INDEX
    Explanations

    peek at or into something

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

    The neuron detects words and word‐fragments that signal taking a quick look or glimpse (e.g. peek, peep, glimpse).

    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
    та
    -1.65
    resor
    -1.61
     télévisée
    -1.58
     Until
    -1.58
    OREM
    -1.57
     Those
    -1.56
     Since
    -1.56
    Ḱ
    -1.55
    槟
    -1.54
    POSITIVE LOGITS
     the
    1.90
    푉
    1.87
    Mitar
    1.84
    Reparto
    1.83
    archiwizowane
    1.80
    SizedBox
    1.80
    きれいな
    1.79
    ݮ
    1.79
     miniaturka
    1.79
    どうやって
    1.79
    Activations Density 0.013%

    No Known Activations