© 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. 22-GEMMASCOPE-RES-131K
    4. 12995
    Prev
    Next
    INDEX
    Explanations

    PCI Alternative. AlterField( ClosedThe Horn

    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_22/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
     HISTORIA
    -1.48
    Leírás
    -1.30
     abiye
    -1.30
    damit
    -1.29
     during
    -1.27
     bunda
    -1.27
     ketika
    -1.25
     ideen
    -1.25
     reizen
    -1.24
    batterie
    -1.23
    POSITIVE LOGITS
    He
    1.38
    u
    1.27
      
    1.27
    M
    1.25
    </em>
    1.24
    B
    1.24
    T
    1.23
     They
    1.22
     áng
    1.22
    N
    1.21
    Activations Density 0.001%

    No Known Activations