© 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. 16-GEMMASCOPE-2-RES-262K
    7. 120012
    Prev
    Next
    INDEX
    Explanations

    history logs and files

    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_16_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
     égard
    0.71
    d
    0.71
    shifting
    0.59
     ограничения
    0.58
     éprou
    0.58
     переста
    0.57
    rotated
    0.57
    far
    0.56
     ограни
    0.56
    wise
    0.55
    POSITIVE LOGITS
     Genome
    0.63
     Monopoly
    0.61
     forefathers
    0.59
    和
    0.56
     Museu
    0.55
     t
    0.54
     Collection
    0.52
    0
    0.52
    姓
    0.52
     grammar
    0.52
    Activations Density 0.001%

    No Known Activations