© 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. 59567
    Prev
    Next
    INDEX
    Explanations

    movie ratings

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

    This neuron never activates on any tokens in these examples, suggesting it’s essentially inactive (i.e. it doesn’t detect any particular pattern).

    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
     usato
    -2.59
     یا
    -2.56
    〰
    -2.44
     uproar
    -2.39
     案内
    -2.38
    櫚
    -2.31
    特
    -2.30
    坦
    -2.30
    קה
    -2.28
     humaine
    -2.28
    POSITIVE LOGITS
    ⟞
    2.75
     procurando
    2.66
     causando
    2.56
     collaborating
    2.44
     varied
    2.42
     colocando
    2.42
     provocando
    2.42
     realizando
    2.39
    その他の
    2.34
     buscando
    2.28
    Activations Density 0.007%

    No Known Activations