© 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. 27600
    Prev
    Next
    INDEX
    Explanations

    know firsthand how

    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
     sempre
    -1.08
     sterren
    -0.98
    always
    -0.94
     futu
    -0.94
     foreseeable
    -0.94
    still
    -0.93
     samenwerking
    -0.92
     touchpad
    -0.92
    ರೆ
    -0.92
     слайд
    -0.91
    POSITIVE LOGITS
     both
    1.51
     can
    1.41
     having
    1.26
     when
    1.16
     difficult
    1.16
    Both
    1.09
     firsthand
    1.07
     ambos
    1.00
     бывает
    0.99
     one
    0.98
    Activations Density 0.024%

    No Known Activations