© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 70619
    Prev
    Next
    INDEX
    Explanations

    pouches, bags, packets, envelopes

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

    The neuron fires on mentions of flexible container packaging—i.e. occurrences of “pouch” or “bag.”

    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
    0
    -1.55
     necesitaba
    -1.20
    which
    -1.16
    ne
    -1.16
     firstname
    -1.15
     koa
    -1.13
     fff
    -1.13
    .
    -1.13
     zakoń
    -1.13
    idxs
    -1.12
    POSITIVE LOGITS
     otras
    1.58
    gbaar
    1.55
    }`;
    1.54
    इटम
    1.48
    ∽
    1.41
     otros
    1.39
    ctivo
    1.38
    жку
    1.38
    ))));
    1.35
    NUMX
    1.34
    Activations Density 0.055%

    No Known Activations