© 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. 7534
    Prev
    Next
    INDEX
    Explanations

    Irish people and concepts

    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
     
    -2.84
    鸸
    -2.70
    淠
    -2.66
    えっ
    -2.64
    氿
    -2.61
     fabricación
    -2.58
    のお話
    -2.56
     "
    -2.55
    ⩴
    -2.53
    だけでなく
    -2.50
    POSITIVE LOGITS
    s
    3.13
    }
    2.70
    🌸
    2.69
    та
    2.66
     retains
    2.53
    💕
    2.45
    吀
    2.44
    🖤
    2.41
     That
    2.36
    тесь
    2.36
    Activations Density 0.006%

    No Known Activations