© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13039
    Prev
    Next
    INDEX
    Explanations

    legal case information

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

    The neuron is picking up standalone multi-digit numeric lines—e.g. page or section numbers.

    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
    ?
    -3.41
    1
    -3.16
    N
    -2.94
    <i>
    -2.84
    the
    -2.80
    "
    -2.78
    ch
    -2.61
    L
    -2.56
     scintill
    -2.44
    -
    -2.42
    POSITIVE LOGITS
     anún
    3.19
    菹
    2.70
    ٳ
    2.69
     informar
    2.66
     modifikasi
    2.66
    以上です
    2.63
     convertido
    2.59
     και
    2.58
     identifiés
    2.58
    』、
    2.56
    Activations Density 0.001%

    No Known Activations