© 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. 9878
    Prev
    Next
    INDEX
    Explanations

    actions or purpose

    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
     such
    -1.28
     Método
    -1.09
    㩒
    -1.04
     ২০১
    -1.04
     hábitat
    -1.02
    dled
    -1.02
     berbagai
    -1.01
    beitung
    -1.01
     Proyecto
    -0.98
    鸸
    -0.98
    POSITIVE LOGITS
    ;
    1.20
    Z
    1.13
     medzi
    1.08
     första
    1.05
    and
    1.05
    matmul
    0.99
     наверное
    0.96
    P
    0.96
     mezi
    0.94
    arp
    0.94
    Activations Density 0.082%

    No Known Activations