© 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. 34-GEMMASCOPE-RES-131K
    7. 48701
    Prev
    Next
    INDEX
    Explanations

    specifying position or time

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

    The neuron is activated by the token “at,” i.e. it detects occurrences of the word “at.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    Garantía
    -1.05
     précédents
    -1.05
     protokol
    -1.04
     précédentes
    -1.03
     turista
    -1.01
    Opinión
    -0.98
     Komun
    -0.98
     réjou
    -0.98
    ając
    -0.96
    weiß
    -0.96
    POSITIVE LOGITS
     least
    1.46
     once
    1.26
     istot
    1.09
     glance
    1.05
    นี่
    1.04
     intervals
    1.04
    の準備
    1.04
     stake
    1.03
    amboo
    0.99
     zrozum
    0.98
    Activations Density 0.046%

    No Known Activations