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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 89841
    Prev
    Next
    INDEX
    Explanations

    osha, Oshawa, Oshie, Isherwood

    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
     usual
    -0.82
    illère
    -0.79
     вечер
    -0.75
    ranch
    -0.73
    mater
    -0.73
    来週
    -0.72
    掲
    -0.71
    何とか
    -0.71
    opus
    -0.71
     beträ
    -0.71
    POSITIVE LOGITS
    ׂ
    0.87
    ्त
    0.78
    ׁ
    0.76
    の場合
    0.75
     степени
    0.75
    cedores
    0.74
    ANTH
    0.73
    𝛥
    0.73
     enfrentan
    0.73
    acje
    0.72
    Activations Density 0.050%

    No Known Activations