© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 13164
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers followed by inning or round

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

    This neuron is specialized to detect ordinal number words (like “second,” “sixth,” “eighth”) typically used to specify innings or other sequential positions.

    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
     from
    -1.70
    4
    -1.43
    hence
    -1.37
    éndose
    -1.32
     darbo
    -1.31
     principio
    -1.30
    IN
    -1.29
    How
    -1.26
    感器
    -1.26
    小小
    -1.25
    POSITIVE LOGITS
     Then
    1.59
    ༀ
    1.52
    ]$
    1.52
    Напомним
    1.45
     пути
    1.44
    aphthalene
    1.39
    wdriver
    1.34
    饜
    1.34
     Outils
    1.34
    ].
    1.34
    Activations Density 0.009%

    No Known Activations