© 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. 10-GEMMASCOPE-RES-131K
    4. 104507
    Prev
    Next
    INDEX
    Explanations

    UIApplication, Oilers, Juniper, BLS

    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
    謦
    -2.47
    or
    -2.45
     gamba
    -2.34
    诓
    -2.34
    ſſen
    -2.31
     ERSITY
    -2.31
     lapto
    -2.23
    but
    -2.23
     felpa
    -2.22
     zorro
    -2.22
    POSITIVE LOGITS
    ↵↵
    2.84
     competitivos
    2.28
    ación
    2.25
     
    2.25
     insidious
    2.22
            
    2.20
     saludables
    2.19
     "
    2.17
     econó
    2.17
     A
    2.11
    Activations Density 0.018%

    No Known Activations