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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 35143
    Prev
    Next
    INDEX
    Explanations

    mathematical functions or arguments

    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
     these
    -1.52
    1
    -1.38
    2
    -1.26
    <bos>
    -1.25
     some
    -1.16
    參考資料
    -1.14
     various
    -1.09
     other
    -1.09
    结语
    -1.08
    5
    -1.07
    POSITIVE LOGITS
    ]}$
    1.23
    ]-
    1.17
    はコチラ
    1.13
    はこちらから
    1.13
    :+:
    1.11
    ״
    1.11
    urants
    1.09
    
    1.09
    xtures
    1.09
    userRepository
    1.08
    Activations Density 0.005%

    No Known Activations