© 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. 67674
    Prev
    Next
    INDEX
    Explanations

    introduces examples

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

    The neuron fires strongly on occurrences of the phrase “such as,” i.e. when text introduces examples.

    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
    );
    -3.05
    孓
    -2.92
     "--
    -2.66
     "";
    -2.58
     "..
    -2.42
    "--
    -2.38
    }),
    -2.34
    。"
    -2.28
    zają
    -2.28
    涷
    -2.25
    POSITIVE LOGITS
    st
    2.73
     venerable
    2.53
     kleinen
    2.39
     häufigsten
    2.33
     notorious
    2.23
    鲠
    2.22
     that
    2.19
     our
    2.16
    苹
    2.16
     ideales
    2.14
    Activations Density 0.047%

    No Known Activations