© 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. 8305
    Prev
    Next
    INDEX
    Explanations

    why we see phenomena

    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
     конце
    0.54
     spécialement
    0.49
    nu
    0.47
    has
    0.47
    الك
    0.46
    ris
    0.46
     심
    0.45
    리
    0.45
     mittler
    0.44
    pricht
    0.44
    POSITIVE LOGITS
    抜群
    0.47
     Electron
    0.43
     זו
    0.41
    ());
    0.41
    ండోత్సర్గము
    0.41
     nå
    0.41
     electrónica
    0.41
    趵
    0.41
     electron
    0.40
     εισ
    0.40
    Activations Density 0.003%

    No Known Activations