© 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. 13611
    Prev
    Next
    INDEX
    Explanations

    material properties and transportation

    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
    }$
    -2.63
    还有
    -2.59
    ’
    -2.47
     aloof
    -2.45
    都是
    -2.38
    。
    -2.27
     boneka
    -2.19
    efits
    -2.16
    ");
    -2.14
     pembun
    -2.13
    POSITIVE LOGITS
    </h4>
    2.53
    ༑
    2.44
     vollständ
    2.38
    衕
    2.38
    鸲
    2.27
    弍
    2.23
    ization
    2.23
     причины
    2.16
    𖥧
    2.16
    ześnie
    2.14
    Activations Density 0.029%

    No Known Activations