© 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. 22-GEMMASCOPE-RES-131K
    7. 33155
    Prev
    Next
    INDEX
    Explanations

    be it is is should it is is is it it is is

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

    The neuron lights up on very common function words (especially pronouns like “I,” “you,” “am,” “the,” etc.).

    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
     superbes
    -1.67
     magnifiques
    -1.63
     variétés
    -1.47
     personnaliser
    -1.47
     sélectionner
    -1.40
    Jegy
    -1.40
     forskellige
    -1.39
    鳚
    -1.38
    meyen
    -1.38
    Daha
    -1.38
    POSITIVE LOGITS
     its
    1.98
     this
    1.72
     it
    1.66
     only
    1.38
     to
    1.37
    ȧ
    1.30
     another
    1.30
     just
    1.29
     is
    1.28
    t
    1.28
    Activations Density 0.029%

    No Known Activations