© 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. 22125
    Prev
    Next
    INDEX
    Explanations

    drummer, alumnus, geographical names

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

    The neuron consistently lights up on content‐bearing noun tokens—especially proper names and technical or domain‐specific terms.

    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
     atractiva
    -2.52
     treasured
    -2.41
    ністю
    -2.33
    嫿
    -2.33
    pegno
    -2.33
    クラシック
    -2.31
    ᯾
    -2.31
    馘
    -2.30
     ་
    -2.28
    ◹
    -2.25
    POSITIVE LOGITS
            
    3.03
    \
    2.86
     But
    2.73
     We
    2.66
    ни
    2.64
    </td>
    2.50
     was
    2.47
     You
    2.45
     According
    2.41
     has
    2.39
    Activations Density 0.004%

    No Known Activations