© 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. 7186
    Prev
    Next
    INDEX
    Explanations

    Troy, Federico, Qi, Tir names

    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
    ⬮
    -3.09
    翼翼
    -2.97
    のだが
    -2.72
    नलोड
    -2.69
    各样的
    -2.66
    </em>
    -2.55
     hábitat
    -2.47
     faldas
    -2.38
     estadounid
    -2.36
    橚
    -2.36
    POSITIVE LOGITS
    "
    3.31
    '
    2.61
            
    2.56
     "",
    2.45
    逦
    2.41
          
    2.38
    ならない
    2.33
        
    2.31
    萏
    2.17
    I
    2.14
    Activations Density 0.011%

    No Known Activations