© 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. 127650
    Prev
    Next
    INDEX
    Explanations

    pier and piercing

    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
    as
    -3.28
    “
    -3.08
    for
    -3.08
    H
    -3.02
    د
    -2.69
    ↵
    -2.64
    或者
    -2.59
    ஂ
    -2.56
    𖤍
    -2.45
    with
    -2.44
    POSITIVE LOGITS
    archiwizowane
    3.66
    臜
    3.25
    孥
    2.97
    
    2.77
    螄
    2.64
    
    2.63
    鹚
    2.58
    ⴱ
    2.52
    珦
    2.52
    耵
    2.50
    Activations Density 0.002%

    No Known Activations