© 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. 10-GEMMASCOPE-RES-131K
    7. 8794
    Prev
    Next
    INDEX
    Explanations

    retaliation

    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
     literaria
    -2.22
     AFTER
    -2.14
     estaban
    -2.13
     позже
    -2.09
     secas
    -2.06
    ol
    -2.06
     mutta
    -2.02
    푙
    -1.98
    蜮
    -1.95
    賔
    -1.95
    POSITIVE LOGITS
    糴
    3.06
    呖
    3.02
     votación
    2.61
    .”
    2.48
     geladeira
    2.33
     convocatoria
    2.31
    🫃
    2.27
    骉
    2.23
    髕
    2.23
     carteira
    2.16
    Activations Density 0.002%

    No Known Activations