© 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-16K
    7. 11711
    Prev
    Next
    INDEX
    Explanations

    instruction, goals, hash

    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_16k_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
    $=
    0.48
    *(
    0.38
    ٢
    0.38
     deposed
    0.35
    1
    0.35
    Sched
    0.34
    *>
    0.34
    file
    0.33
    *:
    0.33
    StartTime
    0.33
    POSITIVE LOGITS
    ′
    0.61
    ″
    0.57
    ️⃣
    0.47
    ьи
    0.43
    ⃣
    0.40
     manhood
    0.38
     wyłącznie
    0.38
     दिवाली
    0.38
     inescap
    0.37
     तहत
    0.37
    Activations Density 0.221%

    No Known Activations