© 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. 127527
    Prev
    Next
    INDEX
    Explanations

    parenting, management, supervision

    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
    '
    -1.48
    :
    -1.35
     in
    -1.27
     \
    -1.26
    ﮩ
    -1.24
     Hauses
    -1.23
     versatile
    -1.18
    értelmű
    -1.17
    (
    -1.17
    </
    -1.16
    POSITIVE LOGITS
     its
    1.91
    檍
    1.88
     overly
    1.59
     Untuk
    1.56
     każdej
    1.52
     poszczegól
    1.48
    }$
    1.45
    𞤢
    1.45
     大きい
    1.42
    鶿
    1.42
    Activations Density 0.029%

    No Known Activations