© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 119131
    Prev
    Next
    INDEX
    Explanations

    in [word]

    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_34/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
    他的
    -1.38
    这个
    -1.29
    这
    -1.28
    と
    -1.15
    を
    -1.13
     всех
    -1.10
    などを
    -1.04
    つまり
    -1.03
    だから
    -1.01
    habited
    -1.01
    POSITIVE LOGITS
     your
    1.34
     accordance
    1.32
    case
    1.22
     our
    1.18
     the
    1.16
    んですよ
    1.09
    の人に
    1.06
    んですよね
    1.03
    lining
    1.00
     welke
    0.99
    Activations Density 0.224%

    No Known Activations