© 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. 34-GEMMASCOPE-RES-131K
    7. 62933
    Prev
    Next
    INDEX
    Explanations

    SPDX license identifiers

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

    The neuron is triggered by SPDX license‐identifier lines (the “SPDX‐License‐Identifier” header tokens).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     základní
    -0.80
     aquifer
    -0.75
     thoáng
    -0.71
     prawdzi
    -0.71
    MANUFACT
    -0.70
    тивная
    -0.69
    PLATES
    -0.68
     Kudos
    -0.66
    gain
    -0.66
     nejlepší
    -0.66
    POSITIVE LOGITS
    弘
    0.69
    歐
    0.68
    television
    0.68
    斋
    0.67
    嫂
    0.67
    亩
    0.65
     Chid
    0.65
    ève
    0.65
     روز
    0.63
     plural
    0.63
    Activations Density 0.071%

    No Known Activations