© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 10659
    Prev
    Next
    INDEX
    Explanations

    people's surnames and affiliations

    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
     kanamycin
    0.38
     OpenCV
    0.38
     percepción
    0.37
    罾
    0.36
    ப்பது
    0.36
     Attention
    0.35
     நன்மை
    0.34
     Inflammation
    0.34
    桕
    0.34
     Bö
    0.34
    POSITIVE LOGITS
    等人
    0.60
     himself
    0.48
    ian
    0.43
    '
    0.43
    esque
    0.41
     ಅವರ
    0.40
     साहब
    0.39
    ский
    0.37
     Pasha
    0.37
    ová
    0.36
    Activations Density 0.023%

    No Known Activations