© 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. 7025
    Prev
    Next
    INDEX
    Explanations

    college of

    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
    '
    -3.64
    ꪻ
    -1.98
    的了
    -1.95
    *
    -1.93
    ),
    -1.91
    甃
    -1.90
    an
    -1.88
    But
    -1.80
    的就
    -1.80
    的服务
    -1.75
    POSITIVE LOGITS
    ⚋
    2.50
    ſſen
    2.48
     ͡°
    2.44
    姈
    2.41
    möglichen
    2.30
    OOTDTY
    2.27
    螽
    2.17
    냑
    2.16
    婞
    2.11
    ſtra
    2.08
    Activations Density 0.022%

    No Known Activations