© 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. 10-GEMMASCOPE-RES-131K
    7. 73055
    Prev
    Next
    INDEX
    Explanations

    pairs of words

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

    The neuron fires on the first nontrivial content word of a new sentence (i.e. the word immediately following a sentence boundary).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    -1.80
     what
    -1.65
     it
    -1.65
     because
    -1.48
     this
    -1.45
    ։
    -1.41
     webbplats
    -1.38
     jednod
    -1.36
    خصص
    -1.34
    ↵
    -1.34
    POSITIVE LOGITS
     of
    2.69
    leyebilirsiniz
    1.53
    については
    1.36
    おすすめです
    1.29
    aucun
    1.27
    Zdroje
    1.25
    Rozm
    1.24
    にします
    1.19
    aucune
    1.19
    łys
    1.18
    Activations Density 0.045%

    No Known Activations