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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11633
    Prev
    Next
    INDEX
    Explanations

    Q: followed by questions, Effect: followed by descriptions

    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_22/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
     this
    -1.47
    来週
    -1.37
     During
    -1.32
     When
    -1.30
     two
    -1.30
     With
    -1.28
     when
    -1.23
     Kerja
    -1.22
    包含
    -1.19
     includes
    -1.18
    POSITIVE LOGITS
    そういった
    1.27
    などが
    1.25
    跩
    1.16
     meistens
    1.15
    からない
    1.14
    っぱり
    1.13
     rong
    1.13
    ,',
    1.13
    </em>
    1.12
    咐
    1.12
    Activations Density 0.001%

    No Known Activations