© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 36170
    Prev
    Next
    INDEX
    Explanations

    css margin and padding

    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
     erlä
    -1.11
    ?』
    -1.07
     antwortete
    -0.98
    !!」
    -0.96
    همچنین
    -0.94
    ɿ
    -0.94
     Riproduzione
    -0.93
    IQUES
    -0.91
    umbnail
    -0.91
    alisis
    -0.91
    POSITIVE LOGITS
     mélang
    1.13
     inwardly
    1.00
    Ь
    0.99
     وبعد
    0.99
     начать
    0.93
     egyéb
    0.92
    で一番
    0.90
     créées
    0.90
     sencillas
    0.89
     собак
    0.89
    Activations Density 0.002%

    No Known Activations