© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68838
    Prev
    Next
    INDEX
    Explanations

    start of sentences or phrases

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

    The neuron is chiefly triggered by the typographic apostrophe character (’).

    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
     similar
    -1.33
    tigte
    -1.20
     玄関
    -1.11
    UpdatedBy
    -1.10
     Lázaro
    -1.10
     Facile
    -1.07
    個室
    -1.07
     key
    -1.06
    这般
    -1.06
    izzera
    -1.04
    POSITIVE LOGITS
     divertidos
    1.36
     divertidas
    1.32
    dragen
    1.30
     divertido
    1.28
     llamaba
    1.27
     intentó
    1.26
     impide
    1.23
     alkoholu
    1.23
    huur
    1.21
     desmotiv
    1.19
    Activations Density 0.125%

    No Known Activations