© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 91869
    Prev
    Next
    INDEX
    Explanations

    past, present, future, groups, science, origin, legal

    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_31_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
     stripping
    0.57
    艰难
    0.49
     비해
    0.48
     सदस्यीय
    0.46
    攢
    0.46
     Ham
    0.46
     प्राइस
    0.46
     धरो
    0.46
    Со
    0.45
     договора
    0.45
    POSITIVE LOGITS
    もら
    0.41
     tuples
    0.40
    :
    0.40
     spoils
    0.40
    ]|[
    0.39
     lucid
    0.39
     coloro
    0.39
     forgot
    0.38
     nurs
    0.38
     minggu
    0.37
    Activations Density 0.010%

    No Known Activations