© 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. 27236
    Prev
    Next
    INDEX
    Explanations

    proclamation

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

    The neuron activates on occurrences of the exact token “all.”

    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
     to
    -1.74
     if
    -1.59
     by
    -1.50
     any
    -1.31
     can
    -1.30
     cannot
    -1.28
     because
    -1.25
     its
    -1.23
     sehr
    -1.21
     having
    -1.20
    POSITIVE LOGITS
    cluding
    1.41
     terrific
    1.31
     generaciones
    1.30
     trozos
    1.28
     lã
    1.25
     például
    1.25
     áng
    1.21
     éléments
    1.18
    ,”
    1.16
     fantastic
    1.16
    Activations Density 0.000%

    No Known Activations