© 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. 35634
    Prev
    Next
    INDEX
    Explanations

    go programming language `main` function

    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
    ковой
    0.40
    ────────────────
    0.38
     Bez
    0.38
     tê
    0.38
     embed
    0.36
    bez
    0.36
     fantas
    0.36
     چیر
    0.36
     несу
    0.36
     թ
    0.35
    POSITIVE LOGITS
    opensource
    0.46
    personal
    0.44
     digital
    0.41
     Terminal
    0.40
    digital
    0.39
    terminal
    0.38
    Personal
    0.38
     brewed
    0.38
    ოს
    0.38
    Digital
    0.38
    Activations Density 0.012%

    No Known Activations