© 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-65K
    7. 29031
    Prev
    Next
    INDEX
    Explanations

    describing people or places

    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
     شدید
    0.45
     sempat
    0.42
     Wireless
    0.40
     फ
    0.40
     Recordings
    0.40
     Wide
    0.39
     ش
    0.39
     تک
    0.39
     پرو
    0.38
    카오
    0.38
    POSITIVE LOGITS
    ３
    0.46
    ख्य
    0.45
    ąć
    0.44
    achs
    0.43
    ività
    0.42
     définir
    0.41
    亰
    0.41
     अलै
    0.40
    ਕ
    0.40
    üge
    0.40
    Activations Density 0.019%

    No Known Activations