© 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. 39356
    Prev
    Next
    INDEX
    Explanations

    cannot find nor see anything

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

    The neuron is detecting sentence boundaries and the common function/transition words at the start of new sentences (e.g. “.” plus “This is,” “An,” etc.).

    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
     then
    -0.91
    احبه
    -0.88
    wok
    -0.86
     Teaser
    -0.86
     questi
    -0.86
     snabbt
    -0.85
    احث
    -0.85
     berikutnya
    -0.85
    already
    -0.83
     Curator
    -0.83
    POSITIVE LOGITS
     nor
    1.54
     tampoco
    1.36
    Instead
    1.22
    Maybe
    1.13
    也没有
    1.07
    nor
    1.07
    也沒有
    1.06
     Maybe
    1.05
     verständ
    1.02
     except
    1.00
    Activations Density 0.070%

    No Known Activations