© 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. 39042
    Prev
    Next
    INDEX
    Explanations

    forms of

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

    The neuron spikes whenever it sees the word “forms.”

    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
    0
    -2.45
    </b>
    -2.28
    𓁹
    -2.06
     venant
    -2.02
     cinq
    -2.02
    ьет
    -2.00
    先是
    -1.95
    ᭝
    -1.95
     rejoint
    -1.95
    ⩴
    -1.91
    POSITIVE LOGITS
    forms
    2.66
    ︓
    2.45
    </h3>
    2.33
    ↑↑↑</
    2.27
     forms
    2.27
     Forms
    2.25
     dasarnya
    2.22
    袮
    2.22
    ⟝
    2.22
    衎
    2.20
    Activations Density 0.011%

    No Known Activations