© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 67045
    Prev
    Next
    INDEX
    Explanations

    parentheses and hyphens

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

    This neuron detects occurrences of the variable name “y” or “Y” when it appears with numeric subscripts, indices, or as parts of variable identifiers (e.g. y_pred, Y_{i,j,k}).

    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
    ).
    -2.55
    ↵
    -2.45
     ),
    -2.38
    </em>
    -2.33
     )
    -2.28
    ”,
    -2.27
    which
    -2.23
    i
    -2.23
    after
    -2.23
    豋
    -2.17
    POSITIVE LOGITS
    だったり
    2.09
     cientos
    2.00
     Alemania
    2.00
     Valores
    1.88
     afbeeldingen
    1.88
     of
    1.88
     Aç
    1.84
     Publicar
    1.80
     descen
    1.79
     Noviembre
    1.79
    Activations Density 0.053%

    No Known Activations