© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 73448
    Prev
    Next
    INDEX
    Explanations

    partial shutdown

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

    principles, disobedience, summer, variants, solution, generally

    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_31_width_262k_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
     করছে
    0.47
     Selasa
    0.47
    💻
    0.45
     বছরের
    0.45
     পাচ্ছে
    0.45
     হয়তো
    0.44
     বেছে
    0.44
    Choosing
    0.44
     ২
    0.42
     Maybe
    0.42
    POSITIVE LOGITS
     heroism
    0.50
     incont
    0.48
     vendido
    0.47
    तोष
    0.46
     anorexia
    0.46
     service
    0.46
    तिक
    0.46
     satisf
    0.45
     aton
    0.45
     sast
    0.44
    Activations Density 0.001%

    No Known Activations