© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113098
    Prev
    Next
    INDEX
    Explanations

    recent past time indicators

    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_10/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
     is
    -1.44
     was
    -1.38
    </h2>
    -1.35
                                  
    -1.23
    <strong>
    -1.23
     株
    -1.21
     —
    -1.18
    ви
    -1.18
    ↵↵
    -1.17
      
    -1.17
    POSITIVE LOGITS
    にします
    1.48
    ParameterLimits
    1.45
     階段
    1.45
     框
    1.41
    しました
    1.38
     أيض
    1.34
     圓
    1.34
     經典
    1.33
     入り口
    1.33
    ナイキ
    1.33
    Activations Density 0.019%

    No Known Activations