© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 144428
    Prev
    Next
    INDEX
    Explanations

    explaining it

    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
    Lok
    0.45
    Wan
    0.40
     dziew
    0.39
     ਨ
    0.39
    ଝ
    0.39
     ώ
    0.39
    Loc
    0.39
     unabhängig
    0.38
    𝖙
    0.38
     εμφ
    0.38
    POSITIVE LOGITS
     quando
    0.50
     dala
    0.49
     sash
    0.43
     cuando
    0.43
     Biblical
    0.43
     custos
    0.42
     aonde
    0.42
    <td>
    0.42
     cheg
    0.42
     periodical
    0.42
    Activations Density 0.003%

    No Known Activations