© 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. 10-GEMMASCOPE-RES-131K
    7. 7574
    Prev
    Next
    INDEX
    Explanations

    Come and explore

    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
     chaleco
    -1.40
    erweise
    -1.31
     following
    -1.29
     cordón
    -1.29
     saludos
    -1.27
     такой
    -1.27
     two
    -1.26
     Entreprises
    -1.24
     Affaires
    -1.24
     importado
    -1.24
    POSITIVE LOGITS
     we
    1.57
    捺
    1.41
     from
    1.41
    sistent
    1.32
    isés
    1.30
    ribue
    1.27
    찍
    1.27
    will
    1.27
    inių
    1.25
    vlá
    1.25
    Activations Density 0.010%

    No Known Activations