© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112329
    Prev
    Next
    INDEX
    Explanations

    cancel

    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
     traducciones
    -2.41
     แต่
    -2.38
    ⧠
    -2.25
     Of
    -2.25
     Problemen
    -2.23
     representan
    -2.20
     เพราะ
    -2.16
     ofrecemos
    -2.14
     tearing
    -2.08
     mohl
    -2.08
    POSITIVE LOGITS
    ↵
    3.64
    with
    2.38
    馘
    2.28
    e
    2.20
    ～　
    2.17
    which
    2.16
    Q
    2.14
    瘜
    2.13
    m
    2.13
     Cancel
    2.13
    Activations Density 0.004%

    No Known Activations