© 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. 31110
    Prev
    Next
    INDEX
    Explanations

    reproduction, distribution, and permitted use

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

    use, modify, distribute

    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
    Selain
    0.50
    权利
    0.49
    Legal
    0.47
    Subtitle
    0.46
    PublicKey
    0.46
    Disclaimer
    0.45
    ཨ
    0.45
    Tidak
    0.45
    Bought
    0.44
     법
    0.44
    POSITIVE LOGITS
     لكن
    0.55
     ancak
    0.48
     ولكن
    0.48
     mutta
    0.47
     snacking
    0.46
     librement
    0.45
    しやすい
    0.45
    を使った
    0.43
     কিন্তু
    0.43
    有望
    0.43
    Activations Density 0.009%

    No Known Activations