© 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. 40-GEMMASCOPE-2-RES-262K
    7. 34181
    Prev
    Next
    INDEX
    Explanations

    adjacent pair

    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
     любо
    0.41
    陸
    0.39
     инде
    0.38
     слишком
    0.38
     якщо
    0.38
    пропетров
    0.37
     recombinant
    0.37
     رفض
    0.37
     そして
    0.37
     दृष्टी
    0.37
    POSITIVE LOGITS
     spread
    0.43
    ₁,
    0.40
     ধাক
    0.40
     Transfer
    0.39
     Spread
    0.39
    spread
    0.38
     transfer
    0.38
     thinly
    0.38
     Ensure
    0.37
     carefully
    0.37
    Activations Density 0.000%

    No Known Activations