© 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. 75209
    Prev
    Next
    INDEX
    Explanations

    medical procedures or treatments

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

    phrases introducing the subjects or participants in a research study.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron never activates on any token—it doesn’t detect any particular pattern.

    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
     it
    -2.08
     this
    -2.06
     that
    -1.63
     these
    -1.60
     there
    -1.52
     zobaczyć
    -1.48
     those
    -1.47
     if
    -1.44
    gencias
    -1.43
    corrhi
    -1.39
    POSITIVE LOGITS
     juf
    1.40
     visse
    1.38
     alho
    1.38
     harmonie
    1.31
     prenn
    1.30
     nabi
    1.27
     pittores
    1.27
     étr
    1.25
     assiste
    1.25
     horloge
    1.24
    Activations Density 0.230%

    No Known Activations