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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74868
    Prev
    Next
    INDEX
    Explanations

    writer, Already, Q

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ᾽
    -1.75
     اندروید
    -1.74
    pantalón
    -1.72
    וּ
    -1.67
    ִּ
    -1.59
    ritsar
    -1.59
    ᾿
    -1.58
    一旁的
    -1.55
    ֶּ
    -1.55
     گوشی
    -1.54
    POSITIVE LOGITS
     is
    1.60
     हमें
    1.54
    ὴν
    1.51
    ὸν
    1.48
     has
    1.48
     сахара
    1.47
     with
    1.47
     we
    1.43
     армии
    1.42
     as
    1.40
    Activations Density 0.000%

    No Known Activations