© 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. 22-GEMMASCOPE-RES-131K
    7. 12830
    Prev
    Next
    INDEX
    Explanations

    numbers or symbols after words/codes

    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_22/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
    fordshire
    -1.24
     игрушки
    -1.12
    èbres
    -1.10
    tening
    -1.09
     detención
    -1.04
    ciled
    -1.01
    osphere
    -1.01
    €™
    -1.01
    uating
    -1.01
    JsonPropertyName
    -1.00
    POSITIVE LOGITS
     största
    1.10
     gemens
    1.02
     väljer
    1.00
     with
    0.91
     at
    0.91
     trenger
    0.84
     ganska
    0.83
     Well
    0.83
    の準備
    0.82
     Want
    0.82
    Activations Density 0.012%

    No Known Activations