© 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. 58519
    Prev
    Next
    INDEX
    Explanations

    since version numbers

    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
     about
    -1.27
     such
    -1.26
     another
    -1.24
     p
    -1.24
    .
    -1.23
     similar
    -1.18
     for
    -1.16
     dieses
    -1.13
    这么
    -1.12
    -
    -1.12
    POSITIVE LOGITS
     their
    1.75
    ﻹ
    1.45
    ﻷ
    1.39
    见状
    1.37
     куртка
    1.37
     nabíz
    1.36
     mereka
    1.35
     primeiros
    1.34
    ícias
    1.34
    愛知
    1.34
    Activations Density 2.395%

    No Known Activations