© 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. 326
    Prev
    Next
    INDEX
    Explanations

    Keywords for code and names

    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
    '
    -1.24
    If
    -1.06
     previously
    -1.05
    oxane
    -0.97
    出
    -0.96
     entire
    -0.95
    ttino
    -0.95
    aniline
    -0.93
     [])
    -0.92
    年以上
    -0.92
    POSITIVE LOGITS
    を実施
    1.03
    頂いた
    0.94
     they
    0.94
    いただいた
    0.94
     görd
    0.94
    💱
    0.93
    もしっかり
    0.92
    を目指す
    0.91
     recomendaciones
    0.91
    蔦
    0.90
    Activations Density 0.000%

    No Known Activations