© 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. 174099
    Prev
    Next
    INDEX
    Explanations

    also won

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

    introducing another item

    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
    0.40
     china
    0.40
     git
    0.39
     Weak
    0.39
     +-
    0.39
     lagi
    0.38
     mutat
    0.38
     Marcel
    0.37
     Nana
    0.37
    fa
    0.37
    POSITIVE LOGITS
     основных
    0.43
    を用いる
    0.43
    방법
    0.42
    Также
    0.41
    북도
    0.40
     employ
    0.40
    ിലും
    0.40
    虽
    0.39
     अन्यथा
    0.39
     কিরূপে
    0.38
    Activations Density 0.019%

    No Known Activations