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. 7576
    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
     in
    -1.14
     just
    -1.09
     so
    -1.09
     not
    -1.09
     even
    -1.05
     an
    -1.02
     almost
    -1.01
     creates
    -1.01
     creating
    -1.00
     Creating
    -1.00
    POSITIVE LOGITS
     praticamente
    1.26
     amd
    1.16
     Dinas
    1.06
     horrid
    1.05
     abd
    1.04
     sooo
    1.04
     diversos
    1.03
     insanely
    1.02
     idiotic
    1.01
     exceptionally
    1.00
    Activations Density 0.002%

    No Known Activations