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. 7706
    Prev
    Next
    INDEX
    Explanations

    agree to or with

    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
    这也是
    -1.05
     filha
    -1.05
    ਗ਼
    -1.02
    🢒
    -1.02
     大きい
    -1.00
    writerow
    -0.98
    athies
    -0.98
     weichen
    -0.98
     ensuing
    -0.97
    神
    -0.97
    POSITIVE LOGITS
     to
    1.98
     that
    1.73
     with
    1.62
     Agree
    1.52
     on
    1.40
     agree
    1.40
    agree
    1.33
     agrees
    1.28
    Agree
    1.25
     AGRE
    1.18
    Activations Density 0.019%

    No Known Activations