© 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. 41-GEMMASCOPE-2-RES-262K
    7. 33756
    Prev
    Next
    INDEX
    Explanations

    ectoderm, mesoderm

    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_all/layer_41_width_262k_l0_big
    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
     Trenton
    0.38
    事業者
    0.38
     стану
    0.37
     tê
    0.37
     Mó
    0.37
     चाल
    0.36
     stan
    0.36
    侕
    0.36
     pressures
    0.35
    CopyWith
    0.35
    POSITIVE LOGITS
     ect
    1.35
    ect
    1.04
    ECT
    0.89
     ECT
    0.88
     ectopic
    0.85
    ecto
    0.84
     ecl
    0.82
    ects
    0.79
     эк
    0.75
     mes
    0.68
    Activations Density 0.004%

    No Known Activations