© 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. 34-GEMMASCOPE-RES-131K
    7. 49767
    Prev
    Next
    INDEX
    Explanations

    really or truly

    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_34/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
    heren
    -0.82
    estima
    -0.81
     decât
    -0.81
     ControllerBase
    -0.80
     keperluan
    -0.79
    עד
    -0.78
    StandardCharsets
    -0.77
     المرجع
    -0.77
     velkommen
    -0.76
    atorio
    -0.75
    POSITIVE LOGITS
     really
    7.91
    Really
    6.00
    really
    5.84
     vraiment
    5.75
     realmente
    5.41
     wirklich
    5.38
     Really
    5.22
     действительно
    4.88
     davvero
    4.84
     truly
    4.75
    Activations Density 0.232%

    No Known Activations