© 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. 14318
    Prev
    Next
    INDEX
    Explanations

    conditions for stage set

    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
     spécialement
    -1.54
    !</
    -1.48
     جديد
    -1.45
     específico
    -1.44
    Ꮠ
    -1.42
    different
    -1.41
     récemment
    -1.41
    いろんな
    -1.40
     ligado
    -1.38
     nowy
    -1.36
    POSITIVE LOGITS
     a
    2.33
     They
    1.50
     -
    1.39
     for
    1.37
     =
    1.36
     irmão
    1.35
     eventually
    1.32
    msleep
    1.29
     szerint
    1.28
    =
    1.28
    Activations Density 0.037%

    No Known Activations