Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 15-GEMMASCOPE-TRANSCODER-16K
    4. 16342
    Prev
    Next
    INDEX
    Explanations

    language relevant to legal rulings on the justification of incidents such as shootings

    oai_token-act-pair · gemini-2.0-flash

    legal justification

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_15/width_16k
    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
    GEBURTSDATUM
    -0.68
    !*\
    -0.63
    __(/*!
    -0.60
    tagHelperRunner
    -0.57
    _]
    -0.55
    "]));
    -0.53
     kaarangay
    -0.52
    contentLoaded
    -0.52
    bidi
    -0.49
     ***!
    -0.49
    POSITIVE LOGITS
     pleaſure
    0.66
    исленность
    0.63
     Monfieur
    0.61
    AsUp
    0.61
     itſelf
    0.57
     саны
    0.56
     للمعارف
    0.56
     anytime
    0.54
     whenever
    0.53
    ativement
    0.53
    Activations Density 1.367%

    No Known Activations