© 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-65K
    7. 47653
    Prev
    Next
    INDEX
    Explanations

    explaining why

    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_65k_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
     или
    0.50
    𝘁
    0.46
    今後
    0.45
    телям
    0.45
    르
    0.44
    ת
    0.44
    ܤ
    0.44
    ం
    0.43
    ｰ
    0.43
    ಾಗಿ
    0.43
    POSITIVE LOGITS
     strangely
    0.47
     curious
    0.46
     the
    0.45
     weird
    0.44
     cleverly
    0.44
     two
    0.44
     gọn
    0.44
     oddly
    0.43
     peek
    0.42
     brilliant
    0.42
    Activations Density 0.003%

    No Known Activations