© 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. 34-GEMMASCOPE-RES-131K
    7. 48723
    Prev
    Next
    INDEX
    Explanations

    statutory rape or bodies

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

    The neuron is triggered by non-standard Latin tokens—subwords containing accented letters, non-ASCII characters (e.g. Japanese kanji), or otherwise “foreign” symbols.

    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
     Wys
    -0.91
    Wys
    -0.83
    taglio
    -0.81
    Jobs
    -0.81
     stains
    -0.79
    Datagram
    -0.78
     stained
    -0.78
     intStringLen
    -0.78
     Solskjaer
    -0.77
    ändige
    -0.77
    POSITIVE LOGITS
     ovviamente
    0.88
     lively
    0.87
     emailAlready
    0.81
     außergewöhn
    0.80
    活着
    0.77
    訖
    0.74
     andererseits
    0.74
     prodotto
    0.72
     domani
    0.71
     abbraccio
    0.70
    Activations Density 0.009%

    No Known Activations