© 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. 9417
    Prev
    Next
    INDEX
    Explanations

    lists and reviews of items

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

    The neuron responds primarily to very common function words and punctuation (i.e. English “stop words” like is, the, I, in, and sentence‐boundary markers).

    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
    しまった
    -1.23
    Poland
    -1.16
     réfé
    -1.14
    »-
    -1.13
     trenger
    -1.13
     łóż
    -1.13
    yip
    -1.12
    posiciones
    -1.12
     lavadora
    -1.09
     acrylique
    -1.09
    POSITIVE LOGITS
     these
    1.41
     they
    1.35
    などを
    1.13
     also
    1.09
     everything
    1.08
    5
    1.06
    4
    1.05
    6
    1.05
     that
    1.02
     lastly
    1.02
    Activations Density 0.018%

    No Known Activations