© 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. 42458
    Prev
    Next
    INDEX
    Explanations

    common sentence starters

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

    The neuron fires on the first lexical or major function word beginning a sentence or clause (i.e. sentence‐initial tokens).

    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
     prêmio
    -1.74
    TokenNameDOT
    -1.59
     Ternyata
    -1.47
     vêtement
    -1.43
     Meksiko
    -1.41
     ícone
    -1.40
    儅
    -1.38
    蓠
    -1.38
    こんばん
    -1.38
     longterm
    -1.36
    POSITIVE LOGITS
     they
    1.53
     as
    1.33
     it
    1.28
    さんへ
    1.27
    </tr>
    1.25
     like
    1.23
     what
    1.22
    </b>
    1.22
     not
    1.21
    ↵
    1.20
    Activations Density 0.004%

    No Known Activations