© 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. 71252
    Prev
    Next
    INDEX
    Explanations

    turned out

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

    The neuron is tuned to detect instances of the word “out” in result-type verb phrases (e.g. “turned out,” “come out”).

    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
    </td>
    -1.73
    </i>
    -1.70
    -1.28
    many
    -1.23
    der
    -1.23
    ”，
    -1.18
    ize
    -1.16
    %%%
    -1.16
    able
    -1.16
    ers
    -1.16
    POSITIVE LOGITS
    ffè
    1.38
    金币
    1.34
    の絵
    1.30
    čia
    1.27
    athyroid
    1.23
     animada
    1.21
    ἐ
    1.20
    ISTOL
    1.20
     decreto
    1.19
     bustling
    1.19
    Activations Density 0.027%
    No Known Activations