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. 7698
    Prev
    Next
    INDEX
    Explanations

    countries and states

    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
     miten
    -0.93
     jä
    -0.93
     aleg
    -0.90
    Surprisingly
    -0.89
     Nordrhein
    -0.87
    Obviously
    -0.85
     Mesmo
    -0.85
    Ironically
    -0.85
     Porém
    -0.84
    Dichloro
    -0.82
    POSITIVE LOGITS
    癱
    0.99
    ension
    0.93
    尷
    0.91
    (/^
    0.90
    ct
    0.90
     Erfüllung
    0.89
    ld
    0.89
    orn
    0.89
    了一遍
    0.89
    UM
    0.88
    Activations Density 0.020%

    No Known Activations