© 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. 22-GEMMASCOPE-RES-131K
    7. 72854
    Prev
    Next
    INDEX
    Explanations

    mathematical and programming symbols

    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
     and
    -1.31
     but
    -1.15
    UCIÓN
    -1.07
    -1.04
     last
    -1.00
     سایر
    -0.96
     haline
    -0.96
    😧
    -0.96
    kmäler
    -0.96
    きました
    -0.93
    POSITIVE LOGITS
     рассказывает
    1.36
        
    1.22
    новништво
    1.21
    んですよね
    1.15
     deaktivi
    1.10
     anklicken
    1.09
     ritratto
    1.09
     Když
    1.09
    Allora
    1.06
     zufried
    1.05
    Activations Density 0.223%

    No Known Activations