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. 8697
    Prev
    Next
    INDEX
    Explanations

    news betterment

    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
     before
    -1.88
     because
    -1.88
     one
    -1.87
     with
    -1.84
     during
    -1.80
     this
    -1.80
     and
    -1.79
     several
    -1.78
     what
    -1.75
     two
    -1.75
    POSITIVE LOGITS
    eight
    1.54
     новых
    1.48
    quite
    1.45
    ఽ
    1.43
    蓠
    1.43
       
    1.39
     strikingly
    1.38
    STARTED
    1.38
     tranquil
    1.33
    씰
    1.33
    Activations Density 0.001%

    No Known Activations