© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 110531
    Prev
    Next
    INDEX
    Explanations

    details

    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
     fechado
    -1.55
    明日は
    -1.54
     bibliothèque
    -1.52
     organizador
    -1.48
     Urin
    -1.45
    聼
    -1.45
    引用元
    -1.44
    の紹介
    -1.43
    ではまた
    -1.43
    を活用
    -1.41
    POSITIVE LOGITS
    .
    1.65
     Einleitung
    1.37
    ()
    1.32
    b
    1.29
     comenzar
    1.27
     empezar
    1.26
    istungen
    1.23
    其
    1.23
     and
    1.21
    diğini
    1.20
    Activations Density 0.034%

    No Known Activations