© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31467
    Prev
    Next
    INDEX
    Explanations

    postedAt: "1d ago"

    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
    judul
    -1.03
     titolo
    -0.99
    firstName
    -0.94
    pageTitle
    -0.94
    titulo
    -0.90
     header
    -0.90
    LECTION
    -0.90
     Title
    -0.89
     Header
    -0.88
    badlogic
    -0.86
    POSITIVE LOGITS
     rating
    1.20
     Ratings
    1.01
     ratings
    1.00
    tags
    0.98
    Rating
    0.97
     Rating
    0.92
     avaliação
    0.91
     tags
    0.91
    RATING
    0.90
    rating
    0.86
    Activations Density 0.008%

    No Known Activations