© 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. 75243
    Prev
    Next
    INDEX
    Explanations

    Font Awesome icons, link or find

    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
    -1.26
    ִּ
    -1.26
     innovative
    -1.24
     godine
    -1.24
    شوف
    -1.19
     in
    -1.14
     requirements
    -1.13
    комплект
    -1.13
     TikTok
    -1.13
     risk
    -1.13
    POSITIVE LOGITS
     EMER
    1.38
     (~(
    1.24
     severa
    1.20
     Negotiable
    1.19
     '-';
    1.19
    这类
    1.19
     départements
    1.16
     venire
    1.14
     النبات
    1.13
    Dota
    1.13
    Activations Density 0.000%

    No Known Activations