© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 130491
    Prev
    Next
    INDEX
    Explanations

    steps server

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Padding
    0.43
    数
    0.40
    Repositories
    0.38
    आ
    0.37
    Safety
    0.36
    chtenstein
    0.35
    ہ
    0.35
    chon
    0.35
     Fau
    0.34
    Harga
    0.34
    POSITIVE LOGITS
    úp
    0.51
     verir
    0.40
    кую
    0.39
     கீ
    0.39
     constitu
    0.39
     Θ
    0.38
     میتوان
    0.38
    pone
    0.38
     SDLK
    0.38
    ☀
    0.38
    Activations Density 0.000%

    No Known Activations