© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34977
    Prev
    Next
    INDEX
    Explanations

    Role, numbers, and specific contexts

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

    The main thing this neuron does is detect the preposition “on.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     when
    -1.70
     this
    -1.38
     it
    -1.30
     their
    -1.27
     for
    -1.24
     what
    -1.24
     other
    -1.20
     after
    -1.19
    When
    -1.14
    when
    -1.12
    POSITIVE LOGITS
     novamente
    1.22
     auswählen
    1.18
     innumer
    1.16
    كما
    1.09
    mentet
    1.09
     prêtre
    1.09
     Activision
    1.08
    욤
    1.08
     Versatile
    1.07
     opět
    1.07
    Activations Density 0.000%

    No Known Activations