© 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. 38589
    Prev
    Next
    INDEX
    Explanations

    code with attributes

    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
     operaciones
    -0.94
     manifestazione
    -0.90
    Saying
    -0.90
     chaves
    -0.87
    overe
    -0.87
     compagnia
    -0.85
    ふと
    -0.84
     klucz
    -0.84
     této
    -0.83
    の後
    -0.82
    POSITIVE LOGITS
     itself
    0.81
     remission
    0.77
     facade
    0.77
    UNIDENTIFIED
    0.76
     felicit
    0.75
    같이
    0.75
    理石
    0.71
    :
    0.71
     because
    0.71
     zaidi
    0.71
    Activations Density 0.013%

    No Known Activations