© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130268
    Prev
    Next
    INDEX
    Explanations

    diverse languages and concepts

    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
    -1.50
     etc
    -0.97
     judiciales
    -0.94
     before
    -0.93
    éc
    -0.90
    hdys
    -0.89
     곳
    -0.89
    føre
    -0.88
     Verbreitung
    -0.88
     et
    -0.87
    POSITIVE LOGITS
     gewünschten
    1.18
    SequentialGroup
    1.11
     portero
    1.08
     Risiko
    1.05
    आई
    1.03
     llavero
    1.03
    感じで
    1.01
    感じです
    1.01
    ஓ
    0.96
    iedades
    0.95
    Activations Density 0.289%

    No Known Activations