© 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. 10-GEMMASCOPE-RES-131K
    7. 974
    Prev
    Next
    INDEX
    Explanations

    caused by

    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_10/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
    </i>
    -2.58
    橚
    -2.58
     شما
    -2.47
    徜
    -2.45
     détaillés
    -2.33
    踱
    -2.31
    柞
    -2.28
    ቭ
    -2.28
    ztes
    -2.27
     jesu
    -2.23
    POSITIVE LOGITS
    <em>
    2.50
    .
    2.44
     anteriormente
    2.31
    '
    2.30
    caused
    2.22
            
    2.08
    她在
    2.03
    "
    1.99
     стоимости
    1.99
    </h4>
    1.99
    Activations Density 0.016%

    No Known Activations