© 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. 44818
    Prev
    Next
    INDEX
    Explanations

    image name or label

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

    The neuron fires on the literal token “IMAGE” (typically in all-caps code or configuration contexts).

    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
    m
    -2.91
    s
    -2.89
    𝄆
    -2.50
    (
    -2.47
    $
    -2.47
    ↵↵
    -2.44
    м
    -2.39
     människor
    -2.38
    н
    -2.34
    ysteine
    -2.20
    POSITIVE LOGITS
    ing
    3.72
    珦
    3.17
    uſe
    2.86
    </h3>
    2.75
    ра
    2.64
    </strong>
    2.56
    遢
    2.52
    ዣ
    2.50
     Alongside
    2.47
    伉
    2.45
    Activations Density 0.011%

    No Known Activations