© 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. 10-GEMMASCOPE-RES-131K
    7. 40478
    Prev
    Next
    INDEX
    Explanations

    percentages and confidence intervals

    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
     does
    -1.81
     just
    -1.74
     oftentimes
    -1.73
     cannot
    -1.73
    ︓
    -1.69
     might
    -1.68
    Уже
    -1.63
    Возможно
    -1.63
    というわけで
    -1.59
    Она
    -1.58
    POSITIVE LOGITS
    핥
    2.08
    部分が
    1.79
    の部分
    1.69
     unul
    1.64
     diversos
    1.63
    翃
    1.62
    に触
    1.62
    anging
    1.59
    /**
    1.59
    covers
    1.58
    Activations Density 0.008%

    No Known Activations