© 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-262K
    7. 38664
    Prev
    Next
    INDEX
    Explanations

    being an open weights model

    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
    ຜະລິດຕ
    0.52
    respArray
    0.50
    媢
    0.47
    CCCO
    0.46
    =’
    0.46
    κτήθηκε
    0.46
     خاتون
    0.46
    𝗰
    0.45
    ẋ
    0.45
    NSError
    0.45
    POSITIVE LOGITS
     ขอ
    0.52
    i
    0.51
     search
    0.50
     ic
    0.48
    I
    0.46
     dich
    0.44
     coach
    0.44
     Weight
    0.44
     Ig
    0.42
    搜索
    0.42
    Activations Density 0.000%

    No Known Activations