© 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. 28093
    Prev
    Next
    INDEX
    Explanations

    news organization names

    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
    に入れる
    -1.05
    の紹介
    -0.95
     publicly
    -0.88
     erscheinen
    -0.86
    话音
    -0.86
     Join
    -0.82
     pensamentos
    -0.81
    と共に
    -0.81
     Them
    -0.80
     perangkat
    -0.80
    POSITIVE LOGITS
     wrze
    1.21
     why
    1.20
     after
    1.13
     about
    1.12
     before
    1.07
    軼
    1.05
     during
    1.00
    issé
    0.97
     when
    0.94
     how
    0.94
    Activations Density 0.015%

    No Known Activations