© 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. 10-GEMMASCOPE-RES-131K
    7. 127237
    Prev
    Next
    INDEX
    Explanations

    world followed by various words

    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
    sprzedam
    -2.09
     reizen
    -1.95
     valentín
    -1.93
     alſo
    -1.89
     queridos
    -1.87
    泚
    -1.87
    蟜
    -1.86
    рення
    -1.84
    饪
    -1.84
     sentada
    -1.83
    POSITIVE LOGITS
    .
    2.44
    as
    2.34
    f
    2.28
    )
    2.28
    <i>
    2.16
    /
    2.16
    os
    2.13
    ti
    2.09
    "
    2.08
    ve
    2.06
    Activations Density 0.030%

    No Known Activations