© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129991
    Prev
    Next
    INDEX
    Explanations

    promoted context

    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
    ).
    -1.87
    <bos>
    -1.63
     wykonane
    -1.50
     \&
    -1.44
    man
    -1.42
    стройка
    -1.42
     „
    -1.40
    ем
    -1.37
    消失了
    -1.36
    nowrap
    -1.33
    POSITIVE LOGITS
     to
    1.74
     kağıt
    1.55
     harita
    1.53
    irlo
    1.47
     kağı
    1.40
    تها
    1.35
     into
    1.34
    
    1.32
     modifikasi
    1.32
     sostanza
    1.32
    Activations Density 0.040%

    No Known Activations