© 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. 142392
    Prev
    Next
    INDEX
    Explanations

    applied in, only venue, question asked, acid residues, stones whose

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

    gut reaction

    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
    })
    0.45
     (%)
    0.44
    IPA
    0.43
    близи
    0.43
     Pty
    0.42
     dwellings
    0.42
    三种
    0.42
    ;\
    0.42
    +/
    0.42
    パール
    0.42
    POSITIVE LOGITS
     კონ
    0.49
     컨
    0.49
     오픈
    0.48
     Aujourd
    0.47
    ॉफ्ट
    0.47
     영국
    0.47
     हीट
    0.46
     شغ
    0.46
     เปิด
    0.46
     오늘
    0.45
    Activations Density 0.001%

    No Known Activations