© 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. 111294
    Prev
    Next
    INDEX
    Explanations

    ends with -ator or -er

    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
     yaklaşık
    -1.53
     about
    -1.41
    assemblée
    -1.38
     increíbles
    -1.34
    hébergement
    -1.34
    ⌓
    -1.33
    Poids
    -1.29
    worship
    -1.29
    Maak
    -1.27
     idyllic
    -1.27
    POSITIVE LOGITS
     so
    1.38
     of
    1.38
    duration
    1.33
    揪
    1.29
     tourner
    1.29
     soirée
    1.22
    jaardag
    1.20
     concreto
    1.16
    vikle
    1.16
     viene
    1.15
    Activations Density 0.060%

    No Known Activations