© 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. 28086
    Prev
    Next
    INDEX
    Explanations

    .panel VM

    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
    ਫ਼
    -1.03
     TÉCNICA
    -1.02
     結果
    -0.92
    かなぁ
    -0.91
    っけ
    -0.91
     slovens
    -0.91
    <bos>
    -0.90
     TÉCN
    -0.90
     materiál
    -0.90
    🎦
    -0.89
    POSITIVE LOGITS
    </h3>
    1.04
    </h6>
    1.02
    </h4>
    1.01
    ₱
    0.99
     ????
    0.95
    ruptedException
    0.92
    ⅜
    0.92
    }
    
    0.92
    his
    0.91
    бр
    0.91
    Activations Density 0.131%

    No Known Activations