© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64393
    Prev
    Next
    INDEX
    Explanations

    left/parent relationships

    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
    Дар
    -0.82
    Длина
    -0.80
    couples
    -0.79
    Ἵ
    -0.77
     Reverse
    -0.77
    FUENTE
    -0.75
    springen
    -0.75
     역
    -0.75
    adaptador
    -0.75
    苡
    -0.74
    POSITIVE LOGITS
     left
    2.58
    left
    1.90
     Left
    1.82
     children
    1.82
    Left
    1.79
    左
    1.62
     daughter
    1.55
     son
    1.55
    getLeft
    1.55
    LEFT
    1.40
    Activations Density 0.014%

    No Known Activations