© 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. 7209
    Prev
    Next
    INDEX
    Explanations

    Dutch language

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

    The neuron fires whenever it sees the character sequence “ext” (e.g. in “ext3”, “extends,” 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_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
     использования
    -1.70
    </sup>
    -1.63
    </h4>
    -1.56
     aplicación
    -1.55
    轨道
    -1.55
    liculas
    -1.55
    ⚋
    -1.54
    </h1>
    -1.51
    PARATION
    -1.51
    ”。
    -1.50
    POSITIVE LOGITS
     fails
    1.63
     sterren
    1.48
     afbeeldingen
    1.44
     obtend
    1.42
     huidige
    1.42
    vermectin
    1.40
     voordelen
    1.40
    alors
    1.38
    ruguay
    1.38
     enmar
    1.37
    Activations Density 0.000%

    No Known Activations