© 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. 22-GEMMASCOPE-RES-131K
    7. 39604
    Prev
    Next
    INDEX
    Explanations

    only / exclusively

    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
    ēju
    -1.11
     jenen
    -0.96
     држа
    -0.95
     verdadera
    -0.94
     its
    -0.93
     this
    -0.92
     from
    -0.91
    するもの
    -0.89
    .“
    -0.89
     jenem
    -0.88
    POSITIVE LOGITS
     uniquement
    1.20
     only
    1.17
     solamente
    1.13
     ausschließlich
    1.06
    ♪♪
    1.02
     только
    1.02
     должна
    1.02
    ➽
    1.00
     даже
    0.99
     posY
    0.99
    Activations Density 0.002%

    No Known Activations