© 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. 78430
    Prev
    Next
    INDEX
    Explanations

    debated

    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
    ោម
    0.59
    Parameterized
    0.50
    Instantiation
    0.50
    Unary
    0.46
    Heap
    0.46
    HighScore
    0.46
    Pseudo
    0.46
    慰
    0.46
    novae
    0.45
    слава
    0.45
    POSITIVE LOGITS
    ه
    0.55
     ¿
    0.48
    د
    0.46
     onward
    0.45
     negligible
    0.45
     Chicago
    0.45
     틀
    0.44
     strength
    0.43
     rä
    0.43
     ¡
    0.43
    Activations Density 0.001%

    No Known Activations