© 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. 34-GEMMASCOPE-RES-131K
    7. 30729
    Prev
    Next
    INDEX
    Explanations

    part

    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
     sostener
    -0.71
    一层
    -0.69
     プラス
    -0.69
     setDate
    -0.69
    gründ
    -0.69
    ynku
    -0.68
     törvény
    -0.68
    冽
    -0.68
    kében
    -0.67
    /*---
    -0.67
    POSITIVE LOGITS
     parts
    4.03
     part
    3.58
    Part
    3.03
    parts
    3.03
     Parts
    2.88
     Part
    2.88
    part
    2.83
    Parts
    2.78
     части
    2.66
     części
    2.64
    Activations Density 0.094%

    No Known Activations