© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26188
    Prev
    Next
    INDEX
    Explanations

    defining terms or phrases

    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
    ּוֹ
    -1.52
     πρ
    -1.46
    ַּ
    -1.34
    ִּ
    -1.32
     detalló
    -1.30
     his
    -1.30
     set
    -1.28
    IonicModule
    -1.27
    nhung
    -1.27
    rimento
    -1.26
    POSITIVE LOGITS
     usage
    1.60
     religieuses
    1.41
    惋
    1.41
    ֩
    1.41
     cristianismo
    1.40
    metti
    1.38
    Usage
    1.38
     mentales
    1.32
    使用
    1.29
     повече
    1.28
    Activations Density 0.124%

    No Known Activations