© 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. 84820
    Prev
    Next
    INDEX
    Explanations

    centered on or between

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

    The neuron detects occurrences of the word “centered” (and its variant “centred”), especially when used to describe something being positioned or focused in/on something.

    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
    ቾ
    -2.30
    чки
    -2.25
     vedno
    -2.17
     menghapus
    -2.16
     lunghi
    -2.13
    瑁
    -2.13
     Premios
    -2.08
    大的
    -2.08
    {
    -2.08
    𓁹
    -2.06
    POSITIVE LOGITS
    on
    2.77
    ႐
    2.66
    𖥦
    2.44
    that
    2.42
    鸶
    2.28
    櫺
    2.13
    侂
    2.09
    </h2>
    2.08
    }$,
    2.06
    ness
    2.05
    Activations Density 0.007%

    No Known Activations