© 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. 40-GEMMASCOPE-2-RES-262K
    7. 1480
    Prev
    Next
    INDEX
    Explanations

    i in range

    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_40_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
    翛
    0.44
    𒁾
    0.40
    MORDOR
    0.40
    Disciplina
    0.39
     Старки
    0.39
    otherArchive
    0.39
    ﭥ
    0.39
    Rustic
    0.38
    澥
    0.37
     quello
    0.37
    POSITIVE LOGITS
     range
    0.82
     in
    0.80
     dalam
    0.77
     trong
    0.76
     în
    0.76
    range
    0.72
     katika
    0.70
     në
    0.65
     में
    0.64
     فى
    0.64
    Activations Density 0.029%

    No Known Activations