© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128440
    Prev
    Next
    INDEX
    Explanations

    sentence starters and questions

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

    The neuron strongly activates on the first meaningful word of a sentence (i.e. tokens appearing at the starts of sentences).

    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
     and
    -1.79
    ”
    -1.54
    Ｒ
    -1.38
    Ｊ
    -1.38
    Ｌ
    -1.36
    hauled
    -1.33
     mathvariant
    -1.33
    }
    -1.27
    嗪
    -1.26
     TIME
    -1.23
    POSITIVE LOGITS
    )$.
    1.56
     They
    1.43
    \}$.
    1.36
    item
    1.32
    section
    1.28
    といって
    1.27
    }$.
    1.27
     apesar
    1.26
     many
    1.26
     people
    1.26
    Activations Density 0.047%

    No Known Activations