© 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. 8593
    Prev
    Next
    INDEX
    Explanations

    highlighted geographical areas

    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
     well
    0.44
    well
    0.42
     illustrious
    0.40
     Well
    0.40
    her
    0.38
    evre
    0.38
     Torrent
    0.38
     -
    0.37
     Her
    0.37
     Defence
    0.36
    POSITIVE LOGITS
     இடத்தில்
    0.44
    শুধু
    0.43
    ▦
    0.41
     quantification
    0.40
     అక్కడ
    0.40
     pausing
    0.38
    糈
    0.38
    罾
    0.38
    ዐይን
    0.38
     रुक
    0.37
    Activations Density 0.003%

    No Known Activations