© 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. 58863
    Prev
    Next
    INDEX
    Explanations

    already plus state

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

    The neuron fires on occurrences of the adverb “already.”

    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
     instead
    -1.84
     soulign
    -1.70
     Then
    -1.65
     And
    -1.64
    €“
    -1.58
     simplemente
    -1.55
     einfach
    -1.53
     You
    -1.52
    ("]");
    -1.45
    ].
    -1.41
    POSITIVE LOGITS
     castillo
    1.53
     Suiza
    1.48
     Chambres
    1.43
     chaqueta
    1.41
     kimdir
    1.41
     chaleco
    1.40
    閬
    1.38
     redondo
    1.38
     árboles
    1.37
    也在
    1.36
    Activations Density 0.010%

    No Known Activations