© 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. 22-GEMMASCOPE-RES-131K
    7. 66314
    Prev
    Next
    INDEX
    Explanations

    interpretation and analysis of data

    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
     enfo
    -0.97
    ײ
    -0.93
    的动作
    -0.93
    ValueGeneration
    -0.92
     WRITER
    -0.86
     Reptiles
    -0.85
     demostra
    -0.84
    嬪
    -0.83
     پس
    -0.83
    技术
    -0.82
    POSITIVE LOGITS
    ⎛
    1.01
     sorpresas
    0.90
    𝑆
    0.90
    orited
    0.88
    WebElementEntity
    0.88
     squishy
    0.86
     by
    0.86
     grayish
    0.85
     fallu
    0.85
     based
    0.85
    Activations Density 0.044%

    No Known Activations