© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 45503
    Prev
    Next
    INDEX
    Explanations

    categorized as or by

    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
    Negative Logits
    }
    -3.28
    i
    -2.80
    h
    -2.78
     That
    -2.45
     letzten
    -2.39
    もの
    -2.39
    you
    -2.34
    它
    -2.31
    e
    -2.28
     Also
    -2.25
    POSITIVE LOGITS
    いかがでしたか
    2.81
    ↵
    2.67
    以上です
    2.61
    就不是
    2.53
    ーーーー
    2.50
    </h4>
    2.42
    ﱠ
    2.38
    ￪
    2.31
    ではまた
    2.31
     principais
    2.28
    Activations Density 0.004%

    No Known Activations