© 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. 19207
    Prev
    Next
    INDEX
    Explanations

    code, commands, and structured data

    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
     rebates
    0.43
    وطه
    0.42
    õ
    0.40
     lã
    0.39
     rebate
    0.38
    らせ
    0.37
    leşt
    0.37
     gorges
    0.37
    ंगामा
    0.36
    ื่น
    0.36
    POSITIVE LOGITS
    を行う
    0.40
    \}
    0.40
     사항
    0.40
    を行います
    0.39
     becomes
    0.39
     মতি
    0.39
     werden
    0.38
     wordt
    0.38
     的
    0.37
    тивная
    0.37
    Activations Density 0.067%

    No Known Activations