© 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. 74008
    Prev
    Next
    INDEX
    Explanations

    extracting input value

    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
    镔
    -1.48
    桄
    -1.46
    زشکی
    -1.38
    籥
    -1.27
     ezek
    -1.27
     it
    -1.25
     help
    -1.25
    pierw
    -1.24
    ダンス
    -1.24
     understandable
    -1.24
    POSITIVE LOGITS
     tinham
    1.45
    妧
    1.41
    鵜
    1.40
     estavam
    1.39
    褫
    1.34
     quién
    1.34
    鄒
    1.28
    Ꮀ
    1.26
    whom
    1.26
     và
    1.25
    Activations Density 0.018%

    No Known Activations