© 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. 99521
    Prev
    Next
    INDEX
    Explanations

    corrugated materials and names

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

    The neuron strongly activates on mentions of “corrugated” and related terms describing corrugated materials (e.g. boards, sheets, cardboard, plastic, steel).

    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
    皷
    -2.84
     Añade
    -2.70
    ꙑ
    -2.66
     figlia
    -2.64
    就是
    -2.63
     nuovi
    -2.63
     esigen
    -2.61
    Cevap
    -2.53
    ⟣
    -2.53
    ⸰
    -2.52
    POSITIVE LOGITS
    ↵
    3.06
     “
    3.00
    n
    2.77
    ”
    2.72
    :
    2.64
    ]
    2.59
    ,”
    2.47
    v
    2.44
    $
    2.44
    <i>
    2.38
    Activations Density 0.004%

    No Known Activations