© 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. 22-GEMMASCOPE-RES-131K
    7. 130064
    Prev
    Next
    INDEX
    Explanations

    domains followed by related concepts

    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
     you
    -1.38
    quarelle
    -1.30
     sorprendió
    -1.23
    つづく
    -1.21
    
    -1.16
    あー
    -1.12
    时间
    -1.12
     negó
    -1.07
    labas
    -1.05
    ことも
    -1.04
    POSITIVE LOGITS
    <bos>
    1.29
     services
    1.16
    って思
    1.05
     in
    1.02
     activities
    1.01
     issues
    1.00
     Belakang
    1.00
     vincere
    0.98
    ebly
    0.98
     状態
    0.97
    Activations Density 0.064%

    No Known Activations