© 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. 22-GEMMASCOPE-RES-131K
    7. 38480
    Prev
    Next
    INDEX
    Explanations

    activities and concepts

    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_22/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
     niitä
    -1.25
     they
    -1.08
     jotka
    -1.07
    ванні
    -0.99
    🦮
    -0.96
     таких
    -0.95
     Musiker
    -0.94
     eivät
    -0.94
    yttää
    -0.94
    包括
    -0.93
    POSITIVE LOGITS
    ꪻ
    1.41
    かもし
    1.31
     itself
    1.28
    谒
    1.17
    вшей
    1.17
     vacía
    1.17
    着一
    1.13
     geda
    1.12
     иной
    1.12
    这件事情
    1.09
    Activations Density 0.057%

    No Known Activations