© 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. 69634
    Prev
    Next
    INDEX
    Explanations

    rollover and over

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

    The neuron fires on any token containing the substring “roll,” such as roll, rollo, rollover, etc.

    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
    t
    -2.42
    ac
    -2.20
     you
    -2.16
    al
    -2.03
    he
    -1.91
    st
    -1.88
    饪
    -1.77
    ak
    -1.76
     is
    -1.72
     to
    -1.71
    POSITIVE LOGITS
    妡
    2.33
    焄
    2.14
    CurtirCurtir
    2.13
    你也
    2.08
    ৹
    1.89
    眉毛
    1.86
    眥
    1.86
     introductory
    1.82
     unconventional
    1.81
     dezelfde
    1.80
    Activations Density 0.004%

    No Known Activations