© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10568
    Prev
    Next
    INDEX
    Explanations

    Eintracht Braunschweig, Content Management, Privacy Information

    np_acts-logits-general · gemini-2.5-flash-lite

    framework core, cybersecurity compliance, childhood education

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     বললো
    0.40
     親
    0.39
     unwavering
    0.38
    amantha
    0.38
    បង្ហ
    0.37
    osition
    0.36
     ス
    0.36
    യ്
    0.36
     INTEGER
    0.36
    Ꭹ
    0.36
    POSITIVE LOGITS
     E
    0.62
    E
    0.54
     EW
    0.52
     EH
    0.51
     EF
    0.49
     EAC
    0.49
     EB
    0.48
     ED
    0.47
     ES
    0.47
    ulièrement
    0.45
    Activations Density 0.563%

    No Known Activations