© 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. 13934
    Prev
    Next
    INDEX
    Explanations

    listing items or categories

    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
     about
    -0.88
     podido
    -0.87
     zowel
    -0.83
     implementations
    -0.83
    icha
    -0.82
    Figli
    -0.82
    hetically
    -0.81
     Tài
    -0.78
    MessageTagHelper
    -0.78
    curriculum
    -0.78
    POSITIVE LOGITS
     including
    1.28
     kuten
    1.02
    Including
    0.96
    尤其是
    0.94
     ausgewählt
    0.90
     включая
    0.89
     insbesondere
    0.89
    MISC
    0.89
    Selected
    0.88
    Miscellaneous
    0.85
    Activations Density 0.213%

    No Known Activations