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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8753
    Prev
    Next
    INDEX
    Explanations

    questions and answers

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     their
    -0.96
     make
    -0.93
     ل
    -0.89
    :^{
    -0.87
     from
    -0.87
     any
    -0.83
     viktig
    -0.82
     last
    -0.82
     every
    -0.81
    毫米
    -0.80
    POSITIVE LOGITS
     Dogecoin
    0.96
     Sheraton
    0.92
     ³
    0.91
     ADAPT
    0.85
     tymp
    0.84
    Accueil
    0.82
     Yugoslav
    0.81
    menubar
    0.81
     抓
    0.79
    ственный
    0.79
    Activations Density 0.005%

    No Known Activations