© 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. 85352
    Prev
    Next
    INDEX
    Explanations

    Jarvis, Planck, Stevie, Decatur, Navajo

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

    The neuron fires most strongly on capitalized proper names (especially surnames and institution names).

    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
    </b>
    -3.31
    2
    -2.44
    Antes
    -2.31
    ６
    -2.30
    ７
    -2.30
    D
    -2.28
    ４
    -2.13
    喈
    -2.13
    １
    -2.13
    </td>
    -2.13
    POSITIVE LOGITS
     alojamientos
    2.77
     ako
    2.38
     horarios
    2.36
    といふ
    2.34
     puertos
    2.33
    ῎
    2.30
    を始め
    2.28
    镲
    2.20
    をしていた
    2.19
    ственная
    2.16
    Activations Density 0.007%

    No Known Activations