© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118145
    Prev
    Next
    INDEX
    Explanations

    special contexts

    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_34/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
     principaux
    -1.13
     general
    -1.03
     principais
    -1.02
     principales
    -0.98
    sä
    -0.98
    ђа
    -0.96
    various
    -0.94
    闆
    -0.94
     principali
    -0.94
    沨
    -0.94
    POSITIVE LOGITS
     special
    1.71
     особы
    1.48
     techniques
    1.46
     designed
    1.41
    special
    1.41
     treatment
    1.38
    Special
    1.36
     considerations
    1.32
     created
    1.30
     khusus
    1.30
    Activations Density 0.047%

    No Known Activations