© 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. 77635
    Prev
    Next
    INDEX
    Explanations

    third-party developers, issues, solstice, server

    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
     INTO
    0.52
    ographique
    0.51
     musée
    0.49
     maîtrise
    0.47
    ও
    0.44
     글로벌
    0.43
     преми
    0.42
     CONCLUSION
    0.42
    ㈜
    0.42
    Companies
    0.42
    POSITIVE LOGITS
    ell
    0.51
    olip
    0.48
    alo
    0.47
    लियों
    0.44
     overweight
    0.43
     Medicines
    0.43
    ین
    0.43
    лии
    0.42
    ಿಸಿದ
    0.42
    ococcus
    0.42
    Activations Density 0.004%

    No Known Activations