© 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. 128843
    Prev
    Next
    INDEX
    Explanations

    code and technical terms

    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
    x
    -1.63
    4
    -1.48
    czeń
    -1.39
    まだまだ
    -1.34
    j
    -1.34
    !’
    -1.31
    u
    -1.29
    g
    -1.27
    …’
    -1.26
     bevat
    -1.25
    POSITIVE LOGITS
    باشد
    1.60
    ,)
    1.48
     a
    1.45
    昝
    1.43
     Перейти
    1.42
    ꦒ
    1.41
    zapatilla
    1.40
     нрави
    1.37
    켓
    1.36
    凃
    1.35
    Activations Density 0.000%

    No Known Activations