© 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. 58903
    Prev
    Next
    INDEX
    Explanations

    short, shorten, shortest, shorted

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

    The neuron flags occurrences of the root “short” (in tokens like short, shorted, shorting, shortcuts, etc.).

    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
    讃
    -2.41
     There
    -2.14
    {
    -2.11
     reempla
    -2.00
    푉
    -1.91
     Ambos
    -1.90
    劭
    -1.88
     orgull
    -1.88
     pájaros
    -1.87
     próximas
    -1.86
    POSITIVE LOGITS
    1
    3.89
    3
    3.86
    6
    3.66
    9
    3.56
    7
    3.39
    5
    3.28
    4
    3.28
    '
    3.22
    an
    2.73
    that
    2.66
    Activations Density 0.039%

    No Known Activations