© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99549
    Prev
    Next
    INDEX
    Explanations

    prepared for

    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_10/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
     D
    -1.84
    :
    -1.63
    I
    -1.56
    S
    -1.52
     H
    -1.51
    D
    -1.49
         
    -1.49
     T
    -1.45
     Do
    -1.45
     E
    -1.43
    POSITIVE LOGITS
    ︲
    1.83
    媗
    1.75
     Nación
    1.71
     tranſ
    1.70
     DISEASES
    1.66
    Même
    1.65
    趿
    1.63
    řízení
    1.63
    ſion
    1.63
    闳
    1.61
    Activations Density 0.022%

    No Known Activations