© 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. 221679
    Prev
    Next
    INDEX
    Explanations

    queue in C++

    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
    馇
    0.39
    Ban
    0.38
    ban
    0.38
     libr
    0.38
     فی
    0.37
    毕业生
    0.37
     peru
    0.36
    捲
    0.36
    虚拟
    0.36
    綦
    0.36
    POSITIVE LOGITS
     Kinney
    0.44
    StoredKeys
    0.43
     व्हा
    0.41
    tags
    0.41
    })^{
    0.40
    র্ভাব
    0.39
     prescriptions
    0.38
    tions
    0.38
     payloads
    0.38
    ór
    0.37
    Activations Density 0.000%

    No Known Activations