© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 80814
    Prev
    Next
    INDEX
    Explanations

    Appeal judgments and dates

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

    The neuron is specifically detecting the “vs.”/“v.” token (i.e. the versus abbreviation with its trailing period).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     नहीं
    -0.87
     Сол
    -0.77
     Arundel
    -0.72
     نہیں
    -0.71
     chaîne
    -0.69
     Casualty
    -0.68
    Mechanic
    -0.68
    dermal
    -0.68
     your
    -0.66
     instant
    -0.66
    POSITIVE LOGITS
    undum
    0.85
    Oil
    0.77
     Artistic
    0.75
     recht
    0.75
    %&
    0.73
    nunca
    0.73
    Ẩ
    0.72
    ̧
    0.72
    icec
    0.72
    dinger
    0.72
    Activations Density 0.007%

    No Known Activations